On 4/30/20 1:33 PM, Wisam Jaddo wrote:
> Add insertion rate calculation feature into flow
> performance application.
>
> The application now provide the ability to test
> insertion rate of specific rte_flow rule, by
> stressing it to the NIC, and calculate the
> insertion rate.
>
> The application offers some options in the command
> line, to configure which rule to apply.
>
> After that the application will start producing
> rules with same pattern but increasing the outer IP
> source address by 1 each time, thus it will give
> different flow each time, and all other items will
> have open masks.
>
> The current design have single core insertion rate.
> In the future we may have a multi core insertion
> rate measurement support in the app.
>
> Signed-off-by: Wisam Jaddo <wis...@mellanox.com>
> ---
> app/test-flow-perf/Makefile | 3 +
> app/test-flow-perf/actions_gen.c | 86 ++++++
> app/test-flow-perf/actions_gen.h | 48 ++++
> app/test-flow-perf/flow_gen.c | 176 ++++++++++++
> app/test-flow-perf/flow_gen.h | 61 ++++
> app/test-flow-perf/items_gen.c | 265 +++++++++++++++++
> app/test-flow-perf/items_gen.h | 68 +++++
> app/test-flow-perf/main.c | 416 +++++++++++++++++++++++++--
> app/test-flow-perf/meson.build | 8 +
> app/test-flow-perf/user_parameters.h | 15 +
> doc/guides/tools/flow-perf.rst | 186 +++++++++++-
> 11 files changed, 1307 insertions(+), 25 deletions(-)
> create mode 100644 app/test-flow-perf/actions_gen.c
> create mode 100644 app/test-flow-perf/actions_gen.h
> create mode 100644 app/test-flow-perf/flow_gen.c
> create mode 100644 app/test-flow-perf/flow_gen.h
> create mode 100644 app/test-flow-perf/items_gen.c
> create mode 100644 app/test-flow-perf/items_gen.h
>
> diff --git a/app/test-flow-perf/Makefile b/app/test-flow-perf/Makefile
> index 45b1fb1464..968c7c60dd 100644
> --- a/app/test-flow-perf/Makefile
> +++ b/app/test-flow-perf/Makefile
> @@ -19,6 +19,9 @@ CFLAGS += -Wno-unused-function
> #
> # all source are stored in SRCS-y
> #
> +SRCS-y += actions_gen.c
> +SRCS-y += flow_gen.c
> +SRCS-y += items_gen.c
> SRCS-y += main.c
>
> include $(RTE_SDK)/mk/rte.app.mk
> diff --git a/app/test-flow-perf/actions_gen.c
> b/app/test-flow-perf/actions_gen.c
> new file mode 100644
> index 0000000000..564ed820e4
> --- /dev/null
> +++ b/app/test-flow-perf/actions_gen.c
> @@ -0,0 +1,86 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + *
> + * The file contains the implementations of actions generators.
> + * Each generator is responsible for preparing it's action instance
> + * and initializing it with needed data.
> + *
> + * Copyright 2020 Mellanox Technologies, Ltd
> + **/
> +
> +#include <sys/types.h>
> +#include <rte_malloc.h>
> +#include <rte_flow.h>
> +#include <rte_ethdev.h>
> +
> +#include "actions_gen.h"
> +#include "user_parameters.h"
> +
> +void
> +gen_mark(void)
> +{
> + mark_action.id = MARK_ID;
> +}
> +
> +void
> +gen_queue(uint16_t queue)
> +{
> + queue_action.index = queue;
> +}
> +
> +void
> +gen_jump(uint16_t next_table)
> +{
> + jump_action.group = next_table;
> +}
It looks like global structures are used above.
It is hardly future-proof taking above words
about multi-core insertion into account.
> +void
> +gen_rss(uint16_t *queues, uint16_t queues_number)
> +{
> + uint16_t queue;
> + struct action_rss_data *rss_data;
It is better to have empty line here, since right now
it looks very misleading taking into account empty
line before NULL check below.
> + rss_data = rte_malloc("rss_data",
> + sizeof(struct action_rss_data), 0);
> +
> + if (rss_data == NULL)
> + rte_exit(EXIT_FAILURE, "No Memory available!");
> +
> + *rss_data = (struct action_rss_data){
> + .conf = (struct rte_flow_action_rss){
> + .func = RTE_ETH_HASH_FUNCTION_DEFAULT,
> + .level = 0,
> + .types = ETH_RSS_IP,
Why does it differ from port RSS types defaults?
> + .key_len = 0,
> + .queue_num = queues_number,
> + .key = 0,
> + .queue = rss_data->queue,
> + },
> + .key = { 0 },
> + .queue = { 0 },
> + };
> +
> + for (queue = 0; queue < queues_number; queue++)
> + rss_data->queue[queue] = queues[queue];
> +
> + rss_action = &rss_data->conf;
> +}
> +
> +void
> +gen_set_meta(void)
> +{
> + meta_action.data = RTE_BE32(META_DATA);
> + meta_action.mask = RTE_BE32(0xffffffff);
> +}
> +
> +void
> +gen_set_tag(void)
> +{
> + tag_action.data = RTE_BE32(META_DATA);
> + tag_action.mask = RTE_BE32(0xffffffff);
> + tag_action.index = TAG_INDEX;
> +}
> +
> +void
> +gen_port_id(void)
> +{
> + port_id.id = PORT_ID_DST;
> +}
Global structures again.
> diff --git a/app/test-flow-perf/actions_gen.h
> b/app/test-flow-perf/actions_gen.h
> new file mode 100644
> index 0000000000..556d48b871
> --- /dev/null
> +++ b/app/test-flow-perf/actions_gen.h
> @@ -0,0 +1,48 @@
> +/** SPDX-License-Identifier: BSD-3-Clause
> + *
> + * This file contains the functions definitions to
> + * generate each supported action.
> + *
> + * Copyright 2020 Mellanox Technologies, Ltd
> + **/
> +
> +#ifndef _ACTION_GEN_
> +#define _ACTION_GEN_
> +
> +struct rte_flow_action_mark mark_action;
> +struct rte_flow_action_queue queue_action;
> +struct rte_flow_action_jump jump_action;
> +struct rte_flow_action_rss *rss_action;
> +struct rte_flow_action_set_meta meta_action;
> +struct rte_flow_action_set_tag tag_action;
> +struct rte_flow_action_port_id port_id;
> +
> +/* Storage for struct rte_flow_action_rss including external data. */
> +struct action_rss_data {
> + struct rte_flow_action_rss conf;
> + uint8_t key[64];
> + uint16_t queue[128];
> +} action_rss_data;
> +
> +void
> +gen_mark(void);
> +
> +void
> +gen_queue(uint16_t queue);
> +
> +void
> +gen_jump(uint16_t next_table);
> +
> +void
> +gen_rss(uint16_t *queues, uint16_t queues_number);
> +
> +void
> +gen_set_meta(void);
> +
> +void
> +gen_set_tag(void);
> +
> +void
> +gen_port_id(void);
> +
> +#endif
> diff --git a/app/test-flow-perf/flow_gen.c b/app/test-flow-perf/flow_gen.c
> new file mode 100644
> index 0000000000..2d42deace9
> --- /dev/null
> +++ b/app/test-flow-perf/flow_gen.c
> @@ -0,0 +1,176 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + *
> + * The file contains the implementations of the method to
> + * fill items, actions & attributes in their corresponding
> + * arrays, and then generate rte_flow rule.
> + *
> + * After the generation. The rule goes to validation then
> + * creation state and then return the results.
> + *
> + * Copyright 2020 Mellanox Technologies, Ltd
> + */
> +
> +#include <stdint.h>
> +
> +#include "flow_gen.h"
> +#include "items_gen.h"
> +#include "actions_gen.h"
> +#include "user_parameters.h"
> +
> +
> +static void
> +fill_attributes(struct rte_flow_attr *attr,
> + uint8_t flow_attrs, uint16_t group)
> +{
> + if (flow_attrs & INGRESS)
> + attr->ingress = 1;
> + if (flow_attrs & EGRESS)
> + attr->egress = 1;
> + if (flow_attrs & TRANSFER)
> + attr->transfer = 1;
> + attr->group = group;
> +}
> +
> +static void
> +fill_items(struct rte_flow_item items[MAX_ITEMS_NUM],
> + uint16_t flow_items, uint32_t outer_ip_src)
> +{
> + uint8_t items_counter = 0;
> +
> + if (flow_items & META_ITEM)
> + add_meta_data(items, items_counter++);
> + if (flow_items & TAG_ITEM)
> + add_meta_tag(items, items_counter++);
> + if (flow_items & ETH_ITEM)
> + add_ether(items, items_counter++);
> + if (flow_items & VLAN_ITEM)
> + add_vlan(items, items_counter++);
> + if (flow_items & IPV4_ITEM)
> + add_ipv4(items, items_counter++, outer_ip_src);
> + if (flow_items & IPV6_ITEM)
> + add_ipv6(items, items_counter++, outer_ip_src);
> + if (flow_items & TCP_ITEM)
> + add_tcp(items, items_counter++);
> + if (flow_items & UDP_ITEM)
> + add_udp(items, items_counter++);
> + if (flow_items & VXLAN_ITEM)
> + add_vxlan(items, items_counter++);
> + if (flow_items & VXLAN_GPE_ITEM)
> + add_vxlan_gpe(items, items_counter++);
> + if (flow_items & GRE_ITEM)
> + add_gre(items, items_counter++);
> + if (flow_items & GENEVE_ITEM)
> + add_geneve(items, items_counter++);
> + if (flow_items & GTP_ITEM)
> + add_gtp(items, items_counter++);
> +
> + items[items_counter].type = RTE_FLOW_ITEM_TYPE_END;
> +}
> +
> +static void
> +fill_actions(struct rte_flow_action actions[MAX_ACTIONS_NUM],
> + uint16_t flow_actions, uint32_t counter, uint16_t next_table)
> +{
> + uint8_t actions_counter = 0;
> + uint16_t queues[RXQs];
> + uint16_t hairpin_queues[HAIRPIN_QUEUES];
> + uint16_t i;
> + struct rte_flow_action_count count_action;
> + uint8_t temp = counter & 0xff;
> +
> + /* None-fate actions */
> + if (flow_actions & MARK_ACTION) {
> + if (!counter)
> + gen_mark();
> + actions[actions_counter].type = RTE_FLOW_ACTION_TYPE_MARK;
> + actions[actions_counter++].conf = &mark_action;
> + }
> + if (flow_actions & COUNT_ACTION) {
> + actions[actions_counter].type = RTE_FLOW_ACTION_TYPE_COUNT;
> + actions[actions_counter++].conf = &count_action;
> + }
> + if (flow_actions & META_ACTION) {
> + if (!counter)
> + gen_set_meta();
> + actions[actions_counter].type = RTE_FLOW_ACTION_TYPE_SET_META;
> + actions[actions_counter++].conf = &meta_action;
> + }
> + if (flow_actions & TAG_ACTION) {
> + if (!counter)
> + gen_set_tag();
> + actions[actions_counter].type = RTE_FLOW_ACTION_TYPE_SET_TAG;
> + actions[actions_counter++].conf = &tag_action;
> + }
> +
> + /* Fate actions */
> + if (flow_actions & QUEUE_ACTION) {
> + gen_queue(counter % RXQs);
> + actions[actions_counter].type = RTE_FLOW_ACTION_TYPE_QUEUE;
> + actions[actions_counter++].conf = &queue_action;
> + }
> + if (flow_actions & RSS_ACTION) {
> + for (i = 0; i < RXQs; i++)
> + queues[i] = (temp >> (i << 1)) & 0x3;
> + gen_rss(queues, RXQs);
> + actions[actions_counter].type = RTE_FLOW_ACTION_TYPE_RSS;
> + actions[actions_counter++].conf = rss_action;
> + }
> + if (flow_actions & JUMP_ACTION) {
> + if (!counter)
> + gen_jump(next_table);
> + actions[actions_counter].type = RTE_FLOW_ACTION_TYPE_JUMP;
> + actions[actions_counter++].conf = &jump_action;
> + }
> + if (flow_actions & PORT_ID_ACTION) {
> + if (!counter)
> + gen_port_id();
> + actions[actions_counter].type = RTE_FLOW_ACTION_TYPE_PORT_ID;
> + actions[actions_counter++].conf = &port_id;
> + }
> + if (flow_actions & DROP_ACTION)
> + actions[actions_counter++].type = RTE_FLOW_ACTION_TYPE_DROP;
> + if (flow_actions & HAIRPIN_QUEUE_ACTION) {
> + gen_queue((counter % HAIRPIN_QUEUES) + RXQs);
> + actions[actions_counter].type = RTE_FLOW_ACTION_TYPE_QUEUE;
> + actions[actions_counter++].conf = &queue_action;
> + }
> + if (flow_actions & HAIRPIN_RSS_ACTION) {
> + for (i = 0; i < HAIRPIN_QUEUES; i++)
> + hairpin_queues[i] = ((temp >> (i << 1)) & 0x3) + RXQs;
> + gen_rss(hairpin_queues, RXQs);
> + actions[actions_counter].type = RTE_FLOW_ACTION_TYPE_RSS;
> + actions[actions_counter++].conf = rss_action;
> + }
> +
> + actions[actions_counter].type = RTE_FLOW_ACTION_TYPE_END;
> +}
> +
> +struct rte_flow *
> +generate_flow(uint16_t port_id,
> + uint16_t group,
> + uint8_t flow_attrs,
> + uint16_t flow_items,
> + uint16_t flow_actions,
> + uint16_t next_table,
> + uint32_t outer_ip_src,
> + struct rte_flow_error *error)
> +{
> + struct rte_flow_attr attr;
> + struct rte_flow_item items[MAX_ITEMS_NUM];
> + struct rte_flow_action actions[MAX_ACTIONS_NUM];
> + struct rte_flow *flow = NULL;
> +
> + memset(items, 0, sizeof(items));
> + memset(actions, 0, sizeof(actions));
> + memset(&attr, 0, sizeof(struct rte_flow_attr));
> +
> + fill_attributes(&attr, flow_attrs, group);
> +
> + fill_actions(actions, flow_actions,
> + outer_ip_src, next_table);
> +
> + fill_items(items, flow_items, outer_ip_src);
> +
> + flow = rte_flow_create(port_id, &attr, items, actions, error);
> + return flow;
> +}
> diff --git a/app/test-flow-perf/flow_gen.h b/app/test-flow-perf/flow_gen.h
> new file mode 100644
> index 0000000000..99cb9e3791
> --- /dev/null
> +++ b/app/test-flow-perf/flow_gen.h
> @@ -0,0 +1,61 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + *
> + * This file contains the items, actions and attributes
> + * definition. And the methods to prepare and fill items,
> + * actions and attributes to generate rte_flow rule.
> + *
> + * Copyright 2020 Mellanox Technologies, Ltd
> + */
> +
> +#ifndef _FLOW_GEN_
> +#define _FLOW_GEN_
> +
> +#include <stdint.h>
> +#include <rte_flow.h>
> +
> +#include "user_parameters.h"
> +
> +/* Items */
> +#define ETH_ITEM 0x0001
> +#define IPV4_ITEM 0x0002
> +#define IPV6_ITEM 0x0004
> +#define VLAN_ITEM 0x0008
> +#define TCP_ITEM 0x0010
> +#define UDP_ITEM 0x0020
> +#define VXLAN_ITEM 0x0040
> +#define VXLAN_GPE_ITEM 0x0080
> +#define GRE_ITEM 0x0100
> +#define GENEVE_ITEM 0x0200
> +#define GTP_ITEM 0x0400
> +#define META_ITEM 0x0800
> +#define TAG_ITEM 0x1000
May be it is better to use (1UL << RTE_FLOW_ITEM_TYPE_ETH) as
flags in bitmask? E.g. define macro:
#define FLOW_ITEM_MASK(_x) \
(UINT64_C(1) << ETH_FLOW_ITEM_ ## _x)
and use as
FLOW_ITEM_MASK(ETH)
> +
> +/* Actions */
> +#define QUEUE_ACTION 0x0001
> +#define MARK_ACTION 0x0002
> +#define JUMP_ACTION 0x0004
> +#define RSS_ACTION 0x0008
> +#define COUNT_ACTION 0x0010
> +#define META_ACTION 0x0020
> +#define TAG_ACTION 0x0040
> +#define DROP_ACTION 0x0080
> +#define PORT_ID_ACTION 0x0100
> +#define HAIRPIN_QUEUE_ACTION 0x0200
> +#define HAIRPIN_RSS_ACTION 0x0400
same as above
> +
> +/* Attributes */
> +#define INGRESS 0x0001
> +#define EGRESS 0x0002
> +#define TRANSFER 0x0004
> +
> +struct rte_flow *
> +generate_flow(uint16_t port_id,
> + uint16_t group,
> + uint8_t flow_attrs,
> + uint16_t flow_items,
> + uint16_t flow_actions,
> + uint16_t next_table,
> + uint32_t outer_ip_src,
> + struct rte_flow_error *error);
> +
> +#endif
> diff --git a/app/test-flow-perf/items_gen.c b/app/test-flow-perf/items_gen.c
> new file mode 100644
> index 0000000000..fb9733d4e7
> --- /dev/null
> +++ b/app/test-flow-perf/items_gen.c
> @@ -0,0 +1,265 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + *
> + * This file contain the implementations of the items
> + * related methods. Each Item have a method to prepare
> + * the item and add it into items array in given index.
> + *
> + * Copyright 2020 Mellanox Technologies, Ltd
> + */
> +
> +#include <stdint.h>
> +#include <rte_flow.h>
> +
> +#include "items_gen.h"
> +#include "user_parameters.h"
> +
> +static struct rte_flow_item_eth eth_spec;
> +static struct rte_flow_item_eth eth_mask;
> +static struct rte_flow_item_vlan vlan_spec;
> +static struct rte_flow_item_vlan vlan_mask;
> +static struct rte_flow_item_ipv4 ipv4_spec;
> +static struct rte_flow_item_ipv4 ipv4_mask;
> +static struct rte_flow_item_ipv6 ipv6_spec;
> +static struct rte_flow_item_ipv6 ipv6_mask;
> +static struct rte_flow_item_udp udp_spec;
> +static struct rte_flow_item_udp udp_mask;
> +static struct rte_flow_item_tcp tcp_spec;
> +static struct rte_flow_item_tcp tcp_mask;
> +static struct rte_flow_item_vxlan vxlan_spec;
> +static struct rte_flow_item_vxlan vxlan_mask;
> +static struct rte_flow_item_vxlan_gpe vxlan_gpe_spec;
> +static struct rte_flow_item_vxlan_gpe vxlan_gpe_mask;
> +static struct rte_flow_item_gre gre_spec;
> +static struct rte_flow_item_gre gre_mask;
> +static struct rte_flow_item_geneve geneve_spec;
> +static struct rte_flow_item_geneve geneve_mask;
> +static struct rte_flow_item_gtp gtp_spec;
> +static struct rte_flow_item_gtp gtp_mask;
> +static struct rte_flow_item_meta meta_spec;
> +static struct rte_flow_item_meta meta_mask;
> +static struct rte_flow_item_tag tag_spec;
> +static struct rte_flow_item_tag tag_mask;
Any global variable usually very bad if you have
a plan to use many CPU cores using threads.
> +
> +
> +void
> +add_ether(struct rte_flow_item items[MAX_ITEMS_NUM],
> + uint8_t items_counter)
> +{
> + memset(ð_spec, 0, sizeof(struct rte_flow_item_eth));
> + memset(ð_mask, 0, sizeof(struct rte_flow_item_eth));
> + eth_spec.type = 0;
> + eth_mask.type = 0;
> +
> + items[items_counter].type = RTE_FLOW_ITEM_TYPE_ETH;
> + items[items_counter].spec = ð_spec;
> + items[items_counter].mask = ð_mask;
> +}
> +
> +void
> +add_vlan(struct rte_flow_item items[MAX_ITEMS_NUM],
> + uint8_t items_counter)
> +{
> + uint16_t vlan_value = VLAN_VALUE;
> + memset(&vlan_spec, 0, sizeof(struct rte_flow_item_vlan));
> + memset(&vlan_mask, 0, sizeof(struct rte_flow_item_vlan));
> +
> + vlan_spec.tci = RTE_BE16(vlan_value);
> + vlan_mask.tci = RTE_BE16(0xffff);
> +
> + items[items_counter].type = RTE_FLOW_ITEM_TYPE_VLAN;
> + items[items_counter].spec = &vlan_spec;
> + items[items_counter].mask = &vlan_mask;
> +}
> +
> +void
> +add_ipv4(struct rte_flow_item items[MAX_ITEMS_NUM],
> + uint8_t items_counter, uint32_t src_ipv4)
> +{
> + memset(&ipv4_spec, 0, sizeof(struct rte_flow_item_ipv4));
> + memset(&ipv4_mask, 0, sizeof(struct rte_flow_item_ipv4));
> +
> + ipv4_spec.hdr.src_addr = src_ipv4;
> + ipv4_mask.hdr.src_addr = 0xffffffff;
> +
> + items[items_counter].type = RTE_FLOW_ITEM_TYPE_IPV4;
> + items[items_counter].spec = &ipv4_spec;
> + items[items_counter].mask = &ipv4_mask;
> +}
> +
> +
> +void
> +add_ipv6(struct rte_flow_item items[MAX_ITEMS_NUM],
> + uint8_t items_counter, int src_ipv6)
> +{
> + memset(&ipv6_spec, 0, sizeof(struct rte_flow_item_ipv6));
> + memset(&ipv6_mask, 0, sizeof(struct rte_flow_item_ipv6));
> +
> + /** Set ipv6 src **/
> + memset(&ipv6_spec.hdr.src_addr, src_ipv6,
> + sizeof(ipv6_spec.hdr.src_addr) / 2);
> +
> + /** Full mask **/
> + memset(&ipv6_mask.hdr.src_addr, 1,
> + sizeof(ipv6_spec.hdr.src_addr));
> +
> + items[items_counter].type = RTE_FLOW_ITEM_TYPE_IPV6;
> + items[items_counter].spec = &ipv6_spec;
> + items[items_counter].mask = &ipv6_mask;
> +}
> +
> +void
> +add_tcp(struct rte_flow_item items[MAX_ITEMS_NUM],
> + uint8_t items_counter)
> +{
> + memset(&tcp_spec, 0, sizeof(struct rte_flow_item_tcp));
> + memset(&tcp_mask, 0, sizeof(struct rte_flow_item_tcp));
> +
> + items[items_counter].type = RTE_FLOW_ITEM_TYPE_TCP;
> + items[items_counter].spec = &tcp_spec;
> + items[items_counter].mask = &tcp_mask;
> +}
> +
> +void
> +add_udp(struct rte_flow_item items[MAX_ITEMS_NUM],
> + uint8_t items_counter)
> +{
> + memset(&udp_spec, 0, sizeof(struct rte_flow_item_udp));
> + memset(&udp_mask, 0, sizeof(struct rte_flow_item_udp));
> +
> + items[items_counter].type = RTE_FLOW_ITEM_TYPE_UDP;
> + items[items_counter].spec = &udp_spec;
> + items[items_counter].mask = &udp_mask;
> +}
> +
> +void
> +add_vxlan(struct rte_flow_item items[MAX_ITEMS_NUM],
> + uint8_t items_counter)
> +{
> + uint32_t vni_value = VNI_VALUE;
> + uint8_t i;
> + memset(&vxlan_spec, 0, sizeof(struct rte_flow_item_vxlan));
> + memset(&vxlan_mask, 0, sizeof(struct rte_flow_item_vxlan));
> +
> + /* Set standard vxlan vni */
> + for (i = 0; i < 3; i++) {
> + vxlan_spec.vni[2 - i] = vni_value >> (i * 8);
> + vxlan_mask.vni[2 - i] = 0xff;
> + }
> +
> + /* Standard vxlan flags **/
> + vxlan_spec.flags = 0x8;
> +
> + items[items_counter].type = RTE_FLOW_ITEM_TYPE_VXLAN;
> + items[items_counter].spec = &vxlan_spec;
> + items[items_counter].mask = &vxlan_mask;
> +}
> +
> +void
> +add_vxlan_gpe(struct rte_flow_item items[MAX_ITEMS_NUM],
> + uint8_t items_counter)
> +{
> + uint32_t vni_value = VNI_VALUE;
> + uint8_t i;
> + memset(&vxlan_gpe_spec, 0, sizeof(struct rte_flow_item_vxlan_gpe));
> + memset(&vxlan_gpe_mask, 0, sizeof(struct rte_flow_item_vxlan_gpe));
> +
> + /* Set vxlan-gpe vni */
> + for (i = 0; i < 3; i++) {
> + vxlan_gpe_spec.vni[2 - i] = vni_value >> (i * 8);
> + vxlan_gpe_mask.vni[2 - i] = 0xff;
> + }
> +
> + /* vxlan-gpe flags */
> + vxlan_gpe_spec.flags = 0x0c;
> +
> + items[items_counter].type = RTE_FLOW_ITEM_TYPE_VXLAN_GPE;
> + items[items_counter].spec = &vxlan_gpe_spec;
> + items[items_counter].mask = &vxlan_gpe_mask;
> +}
> +
> +void
> +add_gre(struct rte_flow_item items[MAX_ITEMS_NUM],
> + uint8_t items_counter)
> +{
> + uint16_t proto = GRE_PROTO;
> + memset(&gre_spec, 0, sizeof(struct rte_flow_item_gre));
> + memset(&gre_mask, 0, sizeof(struct rte_flow_item_gre));
> +
> + gre_spec.protocol = RTE_BE16(proto);
> + gre_mask.protocol = 0xffff;
> +
> + items[items_counter].type = RTE_FLOW_ITEM_TYPE_GRE;
> + items[items_counter].spec = &gre_spec;
> + items[items_counter].mask = &gre_mask;
> +}
> +
> +void
> +add_geneve(struct rte_flow_item items[MAX_ITEMS_NUM],
> + uint8_t items_counter)
> +{
> + uint32_t vni_value = VNI_VALUE;
> + uint8_t i;
> + memset(&geneve_spec, 0, sizeof(struct rte_flow_item_geneve));
> + memset(&geneve_mask, 0, sizeof(struct rte_flow_item_geneve));
> +
> + for (i = 0; i < 3; i++) {
> + geneve_spec.vni[2 - i] = vni_value >> (i * 8);
> + geneve_mask.vni[2 - i] = 0xff;
> + }
> +
> + items[items_counter].type = RTE_FLOW_ITEM_TYPE_GENEVE;
> + items[items_counter].spec = &geneve_spec;
> + items[items_counter].mask = &geneve_mask;
> +}
> +
> +void
> +add_gtp(struct rte_flow_item items[MAX_ITEMS_NUM],
> + uint8_t items_counter)
> +{
> + uint32_t teid_value = TEID_VALUE;
> + memset(>p_spec, 0, sizeof(struct rte_flow_item_gtp));
> + memset(>p_mask, 0, sizeof(struct rte_flow_item_gtp));
> +
> + gtp_spec.teid = RTE_BE32(teid_value);
> + gtp_mask.teid = RTE_BE32(0xffffffff);
> +
> + items[items_counter].type = RTE_FLOW_ITEM_TYPE_GTP;
> + items[items_counter].spec = >p_spec;
> + items[items_counter].mask = >p_mask;
> +}
> +
> +void
> +add_meta_data(struct rte_flow_item items[MAX_ITEMS_NUM],
> + uint8_t items_counter)
> +{
> + uint32_t data = META_DATA;
> + memset(&meta_spec, 0, sizeof(struct rte_flow_item_meta));
> + memset(&meta_mask, 0, sizeof(struct rte_flow_item_meta));
> +
> + meta_spec.data = RTE_BE32(data);
> + meta_mask.data = RTE_BE32(0xffffffff);
> +
> + items[items_counter].type = RTE_FLOW_ITEM_TYPE_META;
> + items[items_counter].spec = &meta_spec;
> + items[items_counter].mask = &meta_mask;
> +}
> +
> +
> +void
> +add_meta_tag(struct rte_flow_item items[MAX_ITEMS_NUM],
> + uint8_t items_counter)
> +{
> + uint32_t data = META_DATA;
> + uint8_t index = TAG_INDEX;
> + memset(&tag_spec, 0, sizeof(struct rte_flow_item_tag));
> + memset(&tag_mask, 0, sizeof(struct rte_flow_item_tag));
> +
> + tag_spec.data = RTE_BE32(data);
> + tag_mask.data = RTE_BE32(0xffffffff);
> + tag_spec.index = index;
> + tag_mask.index = 0xff;
> +
> + items[items_counter].type = RTE_FLOW_ITEM_TYPE_TAG;
> + items[items_counter].spec = &tag_spec;
> + items[items_counter].mask = &tag_mask;
> +}
> diff --git a/app/test-flow-perf/items_gen.h b/app/test-flow-perf/items_gen.h
> new file mode 100644
> index 0000000000..0b01385951
> --- /dev/null
> +++ b/app/test-flow-perf/items_gen.h
> @@ -0,0 +1,68 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + *
> + * This file contains the items related methods
> + *
> + * Copyright 2020 Mellanox Technologies, Ltd
> + */
> +
> +#ifndef _ITEMS_GEN_
> +#define _ITEMS_GEN_
> +
> +#include <stdint.h>
> +#include <rte_flow.h>
> +
> +#include "user_parameters.h"
> +
> +void
> +add_ether(struct rte_flow_item items[MAX_ITEMS_NUM],
> + uint8_t items_counter);
> +
> +void
> +add_vlan(struct rte_flow_item items[MAX_ITEMS_NUM],
> + uint8_t items_counter);
> +
> +void
> +add_ipv4(struct rte_flow_item items[MAX_ITEMS_NUM],
> + uint8_t items_counter, uint32_t src_ipv4);
> +
> +void
> +add_ipv6(struct rte_flow_item items[MAX_ITEMS_NUM],
> + uint8_t items_counter, int src_ipv6);
> +
> +void
> +add_udp(struct rte_flow_item items[MAX_ITEMS_NUM],
> + uint8_t items_counter);
> +
> +void
> +add_tcp(struct rte_flow_item items[MAX_ITEMS_NUM],
> + uint8_t items_counter);
> +
> +void
> +add_vxlan(struct rte_flow_item items[MAX_ITEMS_NUM],
> + uint8_t items_counter);
> +
> +void
> +add_vxlan_gpe(struct rte_flow_item items[MAX_ITEMS_NUM],
> + uint8_t items_counter);
> +
> +void
> +add_gre(struct rte_flow_item items[MAX_ITEMS_NUM],
> + uint8_t items_counter);
> +
> +void
> +add_geneve(struct rte_flow_item items[MAX_ITEMS_NUM],
> + uint8_t items_counter);
> +
> +void
> +add_gtp(struct rte_flow_item items[MAX_ITEMS_NUM],
> + uint8_t items_counter);
> +
> +void
> +add_meta_data(struct rte_flow_item items[MAX_ITEMS_NUM],
> + uint8_t items_counter);
> +
> +void
> +add_meta_tag(struct rte_flow_item items[MAX_ITEMS_NUM],
> + uint8_t items_counter);
> +
> +#endif
> diff --git a/app/test-flow-perf/main.c b/app/test-flow-perf/main.c
> index 156b9ef553..115af4f302 100644
> --- a/app/test-flow-perf/main.c
> +++ b/app/test-flow-perf/main.c
> @@ -49,29 +49,119 @@
> #include <rte_cycles.h>
> #include <rte_memory.h>
>
> +#include "flow_gen.h"
> #include "user_parameters.h"
>
> -static uint32_t nb_lcores;
> +#define MAX_ITERATIONS 100
> +
> +struct rte_flow *flow;
> +static uint8_t flow_group;
> +
> +static uint16_t flow_items;
> +static uint16_t flow_actions;
> +static uint8_t flow_attrs;
> +static volatile bool force_quit;
> +static volatile bool dump_iterations;
> static struct rte_mempool *mbuf_mp;
> +static uint32_t nb_lcores;
> +static uint32_t flows_count;
> +static uint32_t iterations_number;
Global static variables again.
> static void usage(char *progname)
> {
> printf("\nusage: %s", progname);
> + printf("\nControl configurations:\n");
> + printf(" --flows-count=N: to set the number of needed"
> + " flows to insert, default is 4,000,000\n");
> + printf(" --dump-iterations: To print rates for each"
> + " iteration\n");
> +
> + printf("To set flow attributes:\n");
> + printf(" --ingress: set ingress attribute in flows\n");
> + printf(" --egress: set egress attribute in flows\n");
> + printf(" --transfer: set transfer attribute in flows\n");
> + printf(" --group=N: set group for all flows,"
> + " default is 0\n");
> +
> + printf("To set flow items:\n");
> + printf(" --ether: add ether layer in flow items\n");
> + printf(" --vlan: add vlan layer in flow items\n");
> + printf(" --ipv4: add ipv4 layer in flow items\n");
> + printf(" --ipv6: add ipv6 layer in flow items\n");
> + printf(" --tcp: add tcp layer in flow items\n");
> + printf(" --udp: add udp layer in flow items\n");
> + printf(" --vxlan: add vxlan layer in flow items\n");
> + printf(" --vxlan-gpe: add vxlan-gpe layer in flow items\n");
> + printf(" --gre: add gre layer in flow items\n");
> + printf(" --geneve: add geneve layer in flow items\n");
> + printf(" --gtp: add gtp layer in flow items\n");
> + printf(" --meta: add meta layer in flow items\n");
> + printf(" --tag: add tag layer in flow items\n");
> +
> + printf("To set flow actions:\n");
> + printf(" --port-id: add port-id action in flow actions\n");
> + printf(" --rss: add rss action in flow actions\n");
> + printf(" --queue: add queue action in flow actions\n");
> + printf(" --jump: add jump action in flow actions\n");
> + printf(" --mark: add mark action in flow actions\n");
> + printf(" --count: add count action in flow actions\n");
> + printf(" --set-meta: add set meta action in flow actions\n");
> + printf(" --set-tag: add set tag action in flow actions\n");
> + printf(" --drop: add drop action in flow actions\n");
> + printf(" --hairpin-queue: add hairpin-queue action in flow actions\n");
> + printf(" --hairpin-rss: add hairping-rss action in flow actions\n");
> }
>
> static void
> args_parse(int argc, char **argv)
> {
> char **argvopt;
> - int opt;
> + int n, opt;
> int opt_idx;
> static struct option lgopts[] = {
> /* Control */
> { "help", 0, 0, 0 },
> + { "flows-count", 1, 0, 0 },
> + { "dump-iterations", 0, 0, 0 },
> + /* Attributes */
> + { "ingress", 0, 0, 0 },
> + { "egress", 0, 0, 0 },
> + { "transfer", 0, 0, 0 },
> + { "group", 1, 0, 0 },
> + /* Items */
> + { "ether", 0, 0, 0 },
> + { "vlan", 0, 0, 0 },
> + { "ipv4", 0, 0, 0 },
> + { "ipv6", 0, 0, 0 },
> + { "tcp", 0, 0, 0 },
> + { "udp", 0, 0, 0 },
> + { "vxlan", 0, 0, 0 },
> + { "vxlan-gpe", 0, 0, 0 },
> + { "gre", 0, 0, 0 },
> + { "geneve", 0, 0, 0 },
> + { "gtp", 0, 0, 0 },
> + { "meta", 0, 0, 0 },
> + { "tag", 0, 0, 0 },
> + /* Actions */
> + { "port-id", 0, 0, 0 },
> + { "rss", 0, 0, 0 },
> + { "queue", 0, 0, 0 },
> + { "jump", 0, 0, 0 },
> + { "mark", 0, 0, 0 },
> + { "count", 0, 0, 0 },
> + { "set-meta", 0, 0, 0 },
> + { "set-tag", 0, 0, 0 },
> + { "drop", 0, 0, 0 },
> + { "hairpin-queue", 0, 0, 0 },
> + { "hairpin-rss", 0, 0, 0 },
> };
>
> + flow_items = 0;
> + flow_actions = 0;
> + flow_attrs = 0;
> argvopt = argv;
>
> + printf(":: Flow -> ");
> while ((opt = getopt_long(argc, argvopt, "",
> lgopts, &opt_idx)) != EOF) {
> switch (opt) {
> @@ -80,6 +170,140 @@ args_parse(int argc, char **argv)
> usage(argv[0]);
> rte_exit(EXIT_SUCCESS, "Displayed help\n");
> }
> + /* Attributes */
> + if (!strcmp(lgopts[opt_idx].name, "ingress")) {
> + flow_attrs |= INGRESS;
> + printf("ingress ");
> + }
> + if (!strcmp(lgopts[opt_idx].name, "egress")) {
> + flow_attrs |= EGRESS;
> + printf("egress ");
> + }
> + if (!strcmp(lgopts[opt_idx].name, "transfer")) {
> + flow_attrs |= TRANSFER;
> + printf("transfer ");
> + }
> + if (!strcmp(lgopts[opt_idx].name, "group")) {
> + n = atoi(optarg);
> + if (n >= 0)
> + flow_group = n;
> + else
> + rte_exit(EXIT_SUCCESS,
> + "flow group should be >= 0");
> + printf("group %d ", flow_group);
> + }
> + /* Items */
> + if (!strcmp(lgopts[opt_idx].name, "ether")) {
> + flow_items |= ETH_ITEM;
> + printf("ether / ");
> + }
> + if (!strcmp(lgopts[opt_idx].name, "ipv4")) {
> + flow_items |= IPV4_ITEM;
> + printf("ipv4 / ");
> + }
> + if (!strcmp(lgopts[opt_idx].name, "vlan")) {
> + flow_items |= VLAN_ITEM;
> + printf("vlan / ");
> + }
> + if (!strcmp(lgopts[opt_idx].name, "ipv6")) {
> + flow_items |= IPV6_ITEM;
> + printf("ipv6 / ");
> + }
> + if (!strcmp(lgopts[opt_idx].name, "tcp")) {
> + flow_items |= TCP_ITEM;
> + printf("tcp / ");
> + }
> + if (!strcmp(lgopts[opt_idx].name, "udp")) {
> + flow_items |= UDP_ITEM;
> + printf("udp / ");
> + }
> + if (!strcmp(lgopts[opt_idx].name, "vxlan")) {
> + flow_items |= VXLAN_ITEM;
> + printf("vxlan / ");
> + }
> + if (!strcmp(lgopts[opt_idx].name, "vxlan-gpe")) {
> + flow_items |= VXLAN_GPE_ITEM;
> + printf("vxlan-gpe / ");
> + }
> + if (!strcmp(lgopts[opt_idx].name, "gre")) {
> + flow_items |= GRE_ITEM;
> + printf("gre / ");
> + }
> + if (!strcmp(lgopts[opt_idx].name, "geneve")) {
> + flow_items |= GENEVE_ITEM;
> + printf("geneve / ");
> + }
> + if (!strcmp(lgopts[opt_idx].name, "gtp")) {
> + flow_items |= GTP_ITEM;
> + printf("gtp / ");
> + }
> + if (!strcmp(lgopts[opt_idx].name, "meta")) {
> + flow_items |= META_ITEM;
> + printf("meta / ");
> + }
> + if (!strcmp(lgopts[opt_idx].name, "tag")) {
> + flow_items |= TAG_ITEM;
> + printf("tag / ");
> + }
I think it is doable using helper structure statically
filled in, array of it and a loop.
> + /* Actions */
> + if (!strcmp(lgopts[opt_idx].name, "port-id")) {
> + flow_actions |= PORT_ID_ACTION;
> + printf("port-id / ");
> + }
> + if (!strcmp(lgopts[opt_idx].name, "rss")) {
> + flow_actions |= RSS_ACTION;
> + printf("rss / ");
> + }
> + if (!strcmp(lgopts[opt_idx].name, "hairpin-rss")) {
> + flow_actions |= HAIRPIN_RSS_ACTION;
> + printf("hairpin-rss / ");
> + }
> + if (!strcmp(lgopts[opt_idx].name, "queue")) {
> + flow_actions |= QUEUE_ACTION;
> + printf("queue / ");
> + }
> + if (!strcmp(lgopts[opt_idx].name, "hairpin-queue")) {
> + flow_actions |= HAIRPIN_QUEUE_ACTION;
> + printf("hairpin-queue / ");
> + }
> + if (!strcmp(lgopts[opt_idx].name, "jump")) {
> + flow_actions |= JUMP_ACTION;
> + printf("jump / ");
> + }
> + if (!strcmp(lgopts[opt_idx].name, "mark")) {
> + flow_actions |= MARK_ACTION;
> + printf("mark / ");
> + }
> + if (!strcmp(lgopts[opt_idx].name, "count")) {
> + flow_actions |= COUNT_ACTION;
> + printf("count / ");
> + }
> + if (!strcmp(lgopts[opt_idx].name, "set-meta")) {
> + flow_actions |= META_ACTION;
> + printf("set-meta / ");
> + }
> + if (!strcmp(lgopts[opt_idx].name, "set-tag")) {
> + flow_actions |= TAG_ACTION;
> + printf("set-tag / ");
> + }
> + if (!strcmp(lgopts[opt_idx].name, "drop")) {
> + flow_actions |= DROP_ACTION;
> + printf("drop / ");
> + }
Same.
> + /* Control */
> + if (!strcmp(lgopts[opt_idx].name, "flows-count")) {
> + n = atoi(optarg);
> + if (n > (int) iterations_number)
> + flows_count = n;
> + else {
> + printf("\n\nflows_count should be > %d",
> + iterations_number);
> + rte_exit(EXIT_SUCCESS, " ");
> + }
> + }
> + if (!strcmp(lgopts[opt_idx].name, "dump-iterations"))
> + dump_iterations = true;
> break;
> default:
> usage(argv[0]);
> @@ -88,6 +312,128 @@ args_parse(int argc, char **argv)
> break;
> }
> }
> + printf("end_flow\n");
> +}
> +
> +static void
> +print_flow_error(struct rte_flow_error error)
> +{
> + printf("Flow can't be created %d message: %s\n",
> + error.type,
> + error.message ? error.message : "(no stated reason)");
> +}
> +
> +static inline void
> +flows_handler(void)
> +{
> + struct rte_flow_error error;
> + clock_t start_iter, end_iter;
> + double cpu_time_used;
> + double flows_rate;
> + double cpu_time_per_iter[MAX_ITERATIONS];
> + double delta;
> + uint16_t nr_ports;
> + uint32_t i;
> + int port_id;
> + int iter_id;
> + uint32_t eagain_counter = 0;
> +
> + nr_ports = rte_eth_dev_count_avail();
> +
> + for (i = 0; i < MAX_ITERATIONS; i++)
> + cpu_time_per_iter[i] = -1;
> +
> + if (iterations_number > flows_count)
> + iterations_number = flows_count;
> +
> + printf(":: Flows Count per port: %d\n", flows_count);
> +
> + for (port_id = 0; port_id < nr_ports; port_id++) {
> + cpu_time_used = 0;
> + if (flow_group > 0) {
> + /*
> + * Create global rule to jumo into flow_group
> + * This way the app will avoid the default rules
> + *
> + * Golbal rule:
> + * group 0 eth / end actions jump group <flow_group>
> + *
> + */
> + flow = generate_flow(port_id, 0, flow_attrs, ETH_ITEM,
> + JUMP_ACTION, flow_group, 0, &error);
> +
> + if (!flow) {
> + print_flow_error(error);
> + rte_exit(EXIT_FAILURE, "error in creating
> flow");
> + }
> + }
> +
> + /* Insertion Rate */
> + printf("Flows insertion on port = %d\n", port_id);
> + start_iter = clock();
> + for (i = 0; i < flows_count; i++) {
> + do {
> + rte_errno = 0;
> + flow = generate_flow(port_id, flow_group,
> + flow_attrs, flow_items, flow_actions,
> + JUMP_ACTION_TABLE, i, &error);
> + if (!flow)
> + eagain_counter++;
> + } while (rte_errno == EAGAIN);
> +
> + if (force_quit)
> + i = flows_count;
> +
> + if (!flow) {
> + print_flow_error(error);
> + rte_exit(EXIT_FAILURE, "error in creating
> flow");
> + }
> +
> + if (i && !((i + 1) % iterations_number)) {
> + /* Save the insertion rate of each iter */
> + end_iter = clock();
> + delta = (double) (end_iter - start_iter);
> + iter_id = ((i + 1) / iterations_number) - 1;
> + cpu_time_per_iter[iter_id] =
> + delta / CLOCKS_PER_SEC;
> + cpu_time_used += cpu_time_per_iter[iter_id];
> + start_iter = clock();
> + }
> + }
> +
> + /* Iteration rate per iteration */
> + if (dump_iterations)
> + for (i = 0; i < MAX_ITERATIONS; i++) {
> + if (cpu_time_per_iter[i] == -1)
> + continue;
> + delta = (double)(iterations_number /
> + cpu_time_per_iter[i]);
> + flows_rate = delta / 1000;
> + printf(":: Iteration #%d: %d flows "
> + "in %f sec[ Rate = %f K/Sec ]\n",
> + i, iterations_number,
> + cpu_time_per_iter[i], flows_rate);
> + }
> +
> + /* Insertion rate for all flows */
> + flows_rate = ((double) (flows_count / cpu_time_used) / 1000);
> + printf("\n:: Total flow insertion rate -> %f K/Sec\n",
> + flows_rate);
> + printf(":: The time for creating %d in flows %f seconds\n",
> + flows_count, cpu_time_used);
> + printf(":: EAGAIN counter = %d\n", eagain_counter);
> + }
> +}
> +
> +static void
> +signal_handler(int signum)
> +{
> + if (signum == SIGINT || signum == SIGTERM) {
> + printf("\n\nSignal %d received, preparing to exit...\n",
> + signum);
> + printf("Error: Stats are wrong due to sudden signal!\n\n");
> + force_quit = true;
> + }
> }
>
> static void
> @@ -96,6 +442,8 @@ init_port(void)
> int ret;
> uint16_t i, j;
> uint16_t port_id;
> + uint16_t nr_queues;
> + bool hairpin_flag = false;
> uint16_t nr_ports = rte_eth_dev_count_avail();
> struct rte_eth_hairpin_conf hairpin_conf = {
> .peer_count = 1,
> @@ -115,6 +463,13 @@ init_port(void)
> struct rte_eth_rxconf rxq_conf;
> struct rte_eth_dev_info dev_info;
>
> + nr_queues = RXQs;
> + if (flow_actions & HAIRPIN_QUEUE_ACTION ||
> + flow_actions & HAIRPIN_RSS_ACTION) {
> + nr_queues = RXQs + HAIRPIN_QUEUES;
> + hairpin_flag = true;
> + }
> +
> if (nr_ports == 0)
> rte_exit(EXIT_FAILURE, "Error: no port detected\n");
> mbuf_mp = rte_pktmbuf_pool_create("mbuf_pool",
> @@ -134,8 +489,8 @@ init_port(void)
>
> port_conf.txmode.offloads &= dev_info.tx_offload_capa;
> printf(":: initializing port: %d\n", port_id);
> - ret = rte_eth_dev_configure(port_id, RXQs + HAIRPIN_QUEUES,
> - TXQs + HAIRPIN_QUEUES, &port_conf);
> + ret = rte_eth_dev_configure(port_id, nr_queues,
> + nr_queues, &port_conf);
> if (ret < 0)
> rte_exit(EXIT_FAILURE,
> ":: cannot configure device: err=%d,
> port=%u\n",
> @@ -173,26 +528,30 @@ init_port(void)
> ":: promiscuous mode enable failed:
> err=%s, port=%u\n",
> rte_strerror(-ret), port_id);
>
> - for (i = RXQs, j = 0; i < RXQs + HAIRPIN_QUEUES; i++, j++) {
> - hairpin_conf.peers[0].port = port_id;
> - hairpin_conf.peers[0].queue = j + TXQs;
> - ret = rte_eth_rx_hairpin_queue_setup(port_id, i,
> - NR_RXD, &hairpin_conf);
> - if (ret != 0)
> - rte_exit(EXIT_FAILURE,
> - ":: Hairpin rx queue setup failed:
> err=%d, port=%u\n",
> - ret, port_id);
> - }
> + if (hairpin_flag) {
> + for (i = RXQs, j = 0;
> + i < RXQs + HAIRPIN_QUEUES; i++, j++) {
> + hairpin_conf.peers[0].port = port_id;
> + hairpin_conf.peers[0].queue = j + TXQs;
> + ret = rte_eth_rx_hairpin_queue_setup(port_id, i,
> + NR_RXD, &hairpin_conf);
> + if (ret != 0)
> + rte_exit(EXIT_FAILURE,
> + ":: Hairpin rx queue setup
> failed: err=%d, port=%u\n",
> + ret, port_id);
> + }
I think it means that the code should be in a helper
function from the very beginning.
> - for (i = TXQs, j = 0; i < TXQs + HAIRPIN_QUEUES; i++, j++) {
> - hairpin_conf.peers[0].port = port_id;
> - hairpin_conf.peers[0].queue = j + RXQs;
> - ret = rte_eth_tx_hairpin_queue_setup(port_id, i,
> - NR_TXD, &hairpin_conf);
> - if (ret != 0)
> - rte_exit(EXIT_FAILURE,
> - ":: Hairpin tx queue setup failed:
> err=%d, port=%u\n",
> - ret, port_id);
> + for (i = TXQs, j = 0;
> + i < TXQs + HAIRPIN_QUEUES; i++, j++) {
> + hairpin_conf.peers[0].port = port_id;
> + hairpin_conf.peers[0].queue = j + RXQs;
> + ret = rte_eth_tx_hairpin_queue_setup(port_id, i,
> + NR_TXD, &hairpin_conf);
> + if (ret != 0)
> + rte_exit(EXIT_FAILURE,
> + ":: Hairpin tx queue setup
> failed: err=%d, port=%u\n",
> + ret, port_id);
> + }
I think it means that the code should be in a helper
function from the very beginning.
> }
>
> ret = rte_eth_dev_start(port_id);
> @@ -219,6 +578,15 @@ main(int argc, char **argv)
> if (ret < 0)
> rte_exit(EXIT_FAILURE, "EAL init failed\n");
>
> + force_quit = false;
> + dump_iterations = false;
> + flows_count = 4000000;
> + iterations_number = 100000;
> + flow_group = 0;
> +
> + signal(SIGINT, signal_handler);
> + signal(SIGTERM, signal_handler);
> +
> argc -= ret;
> argv += ret;
>
> @@ -232,6 +600,8 @@ main(int argc, char **argv)
> if (nb_lcores <= 1)
> rte_exit(EXIT_FAILURE, "This app needs at least two cores\n");
>
> + flows_handler();
> +
> RTE_LCORE_FOREACH_SLAVE(lcore_id)
>
> if (rte_eal_wait_lcore(lcore_id) < 0)
> diff --git a/app/test-flow-perf/meson.build b/app/test-flow-perf/meson.build
> index ec9bb3b3aa..b3941f5c2d 100644
> --- a/app/test-flow-perf/meson.build
> +++ b/app/test-flow-perf/meson.build
> @@ -5,7 +5,15 @@
> #
> # To build this example as a standalone application with an already-installed
> # DPDK instance, use 'make'
> +name = 'flow_perf'
> +allow_experimental_apis = true
> +cflags += '-Wno-deprecated-declarations'
> +cflags += '-Wunused-function'
>
> sources = files(
> + 'actions_gen.c',
> + 'flow_gen.c',
> + 'items_gen.c',
> 'main.c',
> )
> +deps += ['ethdev']
> diff --git a/app/test-flow-perf/user_parameters.h
> b/app/test-flow-perf/user_parameters.h
> index 56ec7f47b5..1d157430b6 100644
> --- a/app/test-flow-perf/user_parameters.h
> +++ b/app/test-flow-perf/user_parameters.h
> @@ -14,3 +14,18 @@
> #define MBUF_CACHE_SIZE 512
> #define NR_RXD 256
> #define NR_TXD 256
> +
> +/** Items/Actions parameters **/
> +#define JUMP_ACTION_TABLE 2
> +#define VLAN_VALUE 1
> +#define VNI_VALUE 1
> +#define GRE_PROTO 0x6558
> +#define META_DATA 1
> +#define TAG_INDEX 0
> +#define PORT_ID_DST 1
> +#define MARK_ID 1
> +#define TEID_VALUE 1
> +
> +/** Flow items/acctions max size **/
> +#define MAX_ITEMS_NUM 20
> +#define MAX_ACTIONS_NUM 20
> diff --git a/doc/guides/tools/flow-perf.rst b/doc/guides/tools/flow-perf.rst
> index 30ce1b6cc0..62e038c430 100644
> --- a/doc/guides/tools/flow-perf.rst
> +++ b/doc/guides/tools/flow-perf.rst
> @@ -4,7 +4,19 @@
> RTE Flow performance tool
> =========================
>
> -Application for rte_flow performance testing.
> +Application for rte_flow performance testing. The application provide the
> +ability to test insertion rate of specific rte_flow rule, by stressing it
> +to the NIC, and calculate the insertion rate.
> +
> +The application offers some options in the command line, to configure
> +which rule to apply.
> +
> +After that the application will start producing rules with same pattern
> +but increasing the outer IP source address by 1 each time, thus it will
> +give different flow each time, and all other items will have open masks.
> +
> +The current design have single core insertion rate. In the future we may
> +have a multi core insertion rate measurement support in the app.
>
>
> Compiling the Application
> @@ -61,9 +73,179 @@ a ``--`` separator:
>
> .. code-block:: console
>
> - sudo ./test-flow-perf -n 4 -w 08:00.0,dv_flow_en=1 --
> + sudo ./flow_perf -n 4 -w 08:00.0,dv_flow_en=1 -- --ingress --ether
> --ipv4 --queue --flows-count=1000000
>
> The command line options are:
>
> * ``--help``
> Display a help message and quit.
> +
> +* ``--flows-count=N``
> + Set the number of needed flows to insert,
> + where 1 <= N <= "number of flows".
> + The default value is 4,000,000.
> +
> +* ``--dump-iterations``
> + Print rates for each iteration of flows.
> + Default iteration is 1,00,000.
> +
> +
> +Attributes:
> +
> +* ``--ingress``
> + Set Ingress attribute to all flows attributes.
> +
> +* ``--egress``
> + Set Egress attribute to all flows attributes.
> +
> +* ``--transfer``
> + Set Transfer attribute to all flows attributes.
> +
> +* ``--group=N``
> + Set group for all flows, where N >= 0.
> + Default group is 0.
> +
> +Items:
> +
> +* ``--ether``
> + Add Ether item to all flows items, This item have open mask.
> +
> +* ``--vlan``
> + Add VLAN item to all flows items,
> + This item have VLAN value defined in user_parameters.h
> + under ``VNI_VALUE`` with full mask, default value = 1.
> + Other fields are open mask.
> +
> +* ``--ipv4``
> + Add IPv4 item to all flows items,
> + This item have incremental source IP, with full mask.
> + Other fields are open mask.
> +
> +* ``--ipv6``
> + Add IPv6 item to all flows item,
> + This item have incremental source IP, with full mask.
> + Other fields are open mask.
> +
> +* ``--tcp``
> + Add TCP item to all flows items, This item have open mask.
> +
> +* ``--udp``
> + Add UDP item to all flows items, This item have open mask.
> +
> +* ``--vxlan``
> + Add VXLAN item to all flows items,
> + This item have VNI value defined in user_parameters.h
> + under ``VNI_VALUE`` with full mask, default value = 1.
> + Other fields are open mask.
> +
> +* ``--vxlan-gpe``
> + Add VXLAN-GPE item to all flows items,
> + This item have VNI value defined in user_parameters.h
> + under ``VNI_VALUE`` with full mask, default value = 1.
> + Other fields are open mask.
> +
> +* ``--gre``
> + Add GRE item to all flows items,
> + This item have protocol value defined in user_parameters.h
> + under ``GRE_PROTO`` with full mask, default protocol = 0x6558 "Ether"
> + Other fields are open mask.
> +
> +* ``--geneve``
> + Add GENEVE item to all flows items,
> + This item have VNI value defined in user_parameters.h
> + under ``VNI_VALUE`` with full mask, default value = 1.
> + Other fields are open mask.
> +
> +* ``--gtp``
> + Add GTP item to all flows items,
> + This item have TEID value defined in user_parameters.h
> + under ``TEID_VALUE`` with full mask, default value = 1.
> + Other fields are open mask.
> +
> +* ``--meta``
> + Add Meta item to all flows items,
> + This item have data value defined in user_parameters.h
> + under ``META_DATA`` with full mask, default value = 1.
> + Other fields are open mask.
> +
> +* ``--tag``
> + Add Tag item to all flows items,
> + This item have data value defined in user_parameters.h
> + under ``META_DATA`` with full mask, default value = 1.
> +
> + Also it have tag value defined in user_parameters.h
> + under ``TAG_INDEX`` with full mask, default value = 0.
> + Other fields are open mask.
> +
> +
> +Actions:
> +
> +* ``--port-id``
> + Add port redirection action to all flows actions.
> + Port redirection destination is defined in user_parameters.h
> + under PORT_ID_DST, default value = 1.
> +
> +* ``--rss``
> + Add RSS action to all flows actions,
> + The queues in RSS action will be all queues configured
> + in the app.
> +
> +* ``--queue``
> + Add queue action to all flows items,
> + The queue will change in round robin state for each flow.
> +
> + For example:
> + The app running with 4 RX queues
> + Flow #0: queue index 0
> + Flow #1: queue index 1
> + Flow #2: queue index 2
> + Flow #3: queue index 3
> + Flow #4: queue index 0
> + ...
> +
> +* ``--jump``
> + Add jump action to all flows actions.
> + Jump action destination is defined in user_parameters.h
> + under ``JUMP_ACTION_TABLE``, default value = 2.
> +
> +* ``--mark``
> + Add mark action to all flows actions.
> + Mark action id is defined in user_parameters.h
> + under ``MARK_ID``, default value = 1.
> +
> +* ``--count``
> + Add count action to all flows actions.
> +
> +* ``--set-meta``
> + Add set-meta action to all flows actions.
> + Meta data is defined in user_parameters.h under ``META_DATA``
> + with full mask, default value = 1.
> +
> +* ``--set-tag``
> + Add set-tag action to all flows actions.
> + Meta data is defined in user_parameters.h under ``META_DATA``
> + with full mask, default value = 1.
> +
> + Tag index is defined in user_parameters.h under ``TAG_INDEX``
> + with full mask, default value = 0.
> +
> +* ``--drop``
> + Add drop action to all flows actions.
> +
> +* ``--hairpin-queue``
> + Add hairpin queue action to all flows actions.
> + The queue will change in round robin state for each flow.
> +
> + For example:
> + The app running with 4 RX hairpin queues and 4 normal RX queues
> + Flow #0: queue index 4
> + Flow #1: queue index 5
> + Flow #2: queue index 6
> + Flow #3: queue index 7
> + Flow #4: queue index 4
> + ...
> +
> +* ``--hairpin-rss``
> + Add hairpin RSS action to all flows actions.
> + The queues in RSS action will be all hairpin queues configured
> + in the app.
>
