* Re: [dpdk-dev] [PATCH] app/flow-perf: add destination ports parameter
2021-10-12 3:42 [dpdk-dev] [PATCH] app/flow-perf: add destination ports parameter Sean Zhang
@ 2021-10-12 7:10 ` Wisam Monther
2021-10-12 7:53 ` Wisam Monther
` (4 subsequent siblings)
5 siblings, 0 replies; 14+ messages in thread
From: Wisam Monther @ 2021-10-12 7:10 UTC (permalink / raw)
To: Sean Zhang (Networking SW), NBU-Contact-Thomas Monjalon
Cc: dev, Raslan Darawsheh
Hi,
> -----Original Message-----
> From: Sean Zhang (Networking SW) <xiazhang@nvidia.com>
> Sent: Tuesday, October 12, 2021 6:43 AM
> To: NBU-Contact-Thomas Monjalon <thomas@monjalon.net>; Wisam
> Monther <wisamm@nvidia.com>
> Cc: dev@dpdk.org; Raslan Darawsheh <rasland@nvidia.com>
> Subject: [PATCH] app/flow-perf: add destination ports parameter
>
> Add destination ports(dst-ports) parameter for port-id action, the parameter
> is only valid for port-id action. The parameter is not Must, and the value is 1
> by default as before if not provided.
>
> For example:
>
> $ dpdk-test-flow-perf -w 08:00.0,representor=[0,1] -- --transfer \
> > --ingress --transfer --ether --portmask=0x2 --vxlan-encap \ --port-id
> > --dst-ports=0
>
> This command means the rule created on representor 0 with port 0 as
> destination, since the portmask is 0x2 and dst-ports is 0:
>
> $ dpdk-test-flow-perf -w 08:00.0,representor=[0,1] \
> > -w 08:00.1,representor=[0,1]-- --transfer --ingress --transfer \
> > --ether --portmask=0x12 --vxlan-encap --port-id --dst-ports=0,3
>
> This command means the rules created on both representor 0 of PF 0 and PF
> 1, the destination port for the first represontor is PF 0, and the destination
> port for the other one it PF 1.
>
> Signed-off-by: Sean Zhang <xiazhang@nvidia.com>
Reviewed-by: Wisam Jaddo <wisamm@nvidia.com>
BRs,
Wisam Jaddo
^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [dpdk-dev] [PATCH] app/flow-perf: add destination ports parameter
2021-10-12 3:42 [dpdk-dev] [PATCH] app/flow-perf: add destination ports parameter Sean Zhang
2021-10-12 7:10 ` Wisam Monther
@ 2021-10-12 7:53 ` Wisam Monther
2021-10-12 8:14 ` Sean Zhang (Networking SW)
2021-10-13 7:44 ` [dpdk-dev] [V2] " Sean Zhang
` (3 subsequent siblings)
5 siblings, 1 reply; 14+ messages in thread
From: Wisam Monther @ 2021-10-12 7:53 UTC (permalink / raw)
To: Sean Zhang (Networking SW), NBU-Contact-Thomas Monjalon
Cc: dev, Raslan Darawsheh
Hi,
> -----Original Message-----
> From: Sean Zhang (Networking SW) <xiazhang@nvidia.com>
> Sent: Tuesday, October 12, 2021 6:43 AM
> To: NBU-Contact-Thomas Monjalon <thomas@monjalon.net>; Wisam
> Monther <wisamm@nvidia.com>
> Cc: dev@dpdk.org; Raslan Darawsheh <rasland@nvidia.com>
> Subject: [PATCH] app/flow-perf: add destination ports parameter
>
> Add destination ports(dst-ports) parameter for port-id action, the parameter
> is only valid for port-id action. The parameter is not Must, and the value is 1
> by default as before if not provided.
>
> For example:
>
> $ dpdk-test-flow-perf -w 08:00.0,representor=[0,1] -- --transfer \
> > --ingress --transfer --ether --portmask=0x2 --vxlan-encap \ --port-id
> > --dst-ports=0
>
> This command means the rule created on representor 0 with port 0 as
> destination, since the portmask is 0x2 and dst-ports is 0:
>
> $ dpdk-test-flow-perf -w 08:00.0,representor=[0,1] \
> > -w 08:00.1,representor=[0,1]-- --transfer --ingress --transfer \
> > --ether --portmask=0x12 --vxlan-encap --port-id --dst-ports=0,3
>
> This command means the rules created on both representor 0 of PF 0 and PF
> 1, the destination port for the first represontor is PF 0, and the destination
> port for the other one it PF 1.
>
> Signed-off-by: Sean Zhang <xiazhang@nvidia.com>
Do you think it's applicable to use the same option?
I mean, usage:
--port-id: means default.
--port-id=N,M: use the parsing ports?
BRs,
Wisam Jaddo
^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [dpdk-dev] [PATCH] app/flow-perf: add destination ports parameter
2021-10-12 7:53 ` Wisam Monther
@ 2021-10-12 8:14 ` Sean Zhang (Networking SW)
2021-10-12 8:15 ` Wisam Monther
0 siblings, 1 reply; 14+ messages in thread
From: Sean Zhang (Networking SW) @ 2021-10-12 8:14 UTC (permalink / raw)
To: Wisam Monther, NBU-Contact-Thomas Monjalon; +Cc: dev, Raslan Darawsheh
Hi Wisam,
> -----Original Message-----
> From: Wisam Monther <wisamm@nvidia.com>
> Sent: Tuesday, October 12, 2021 3:53 PM
> To: Sean Zhang (Networking SW) <xiazhang@nvidia.com>; NBU-Contact-
> Thomas Monjalon <thomas@monjalon.net>
> Cc: dev@dpdk.org; Raslan Darawsheh <rasland@nvidia.com>
> Subject: RE: [PATCH] app/flow-perf: add destination ports parameter
>
> Hi,
>
> > -----Original Message-----
> > From: Sean Zhang (Networking SW) <xiazhang@nvidia.com>
> > Sent: Tuesday, October 12, 2021 6:43 AM
> > To: NBU-Contact-Thomas Monjalon <thomas@monjalon.net>; Wisam
> Monther
> > <wisamm@nvidia.com>
> > Cc: dev@dpdk.org; Raslan Darawsheh <rasland@nvidia.com>
> > Subject: [PATCH] app/flow-perf: add destination ports parameter
> >
> > Add destination ports(dst-ports) parameter for port-id action, the
> > parameter is only valid for port-id action. The parameter is not Must,
> > and the value is 1 by default as before if not provided.
> >
> > For example:
> >
> > $ dpdk-test-flow-perf -w 08:00.0,representor=[0,1] -- --transfer \
> > > --ingress --transfer --ether --portmask=0x2 --vxlan-encap \
> > > --port-id
> > > --dst-ports=0
> >
> > This command means the rule created on representor 0 with port 0 as
> > destination, since the portmask is 0x2 and dst-ports is 0:
> >
> > $ dpdk-test-flow-perf -w 08:00.0,representor=[0,1] \
> > > -w 08:00.1,representor=[0,1]-- --transfer --ingress --transfer \
> > > --ether --portmask=0x12 --vxlan-encap --port-id --dst-ports=0,3
> >
> > This command means the rules created on both representor 0 of PF 0 and
> > PF 1, the destination port for the first represontor is PF 0, and the
> > destination port for the other one it PF 1.
> >
> > Signed-off-by: Sean Zhang <xiazhang@nvidia.com>
>
> Do you think it's applicable to use the same option?
> I mean, usage:
> --port-id: means default.
> --port-id=N,M: use the parsing ports?
Yes, since the argument can be optional, your suggestion is applicable. So do you suggest to change to --port-id=N,M?
>
> BRs,
> Wisam Jaddo
^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [dpdk-dev] [PATCH] app/flow-perf: add destination ports parameter
2021-10-12 8:14 ` Sean Zhang (Networking SW)
@ 2021-10-12 8:15 ` Wisam Monther
2021-10-12 8:22 ` Sean Zhang (Networking SW)
0 siblings, 1 reply; 14+ messages in thread
From: Wisam Monther @ 2021-10-12 8:15 UTC (permalink / raw)
To: Sean Zhang (Networking SW), NBU-Contact-Thomas Monjalon
Cc: dev, Raslan Darawsheh
> -----Original Message-----
> From: Sean Zhang (Networking SW) <xiazhang@nvidia.com>
> Sent: Tuesday, October 12, 2021 11:14 AM
> To: Wisam Monther <wisamm@nvidia.com>; NBU-Contact-Thomas
> Monjalon <thomas@monjalon.net>
> Cc: dev@dpdk.org; Raslan Darawsheh <rasland@nvidia.com>
> Subject: RE: [PATCH] app/flow-perf: add destination ports parameter
>
> Hi Wisam,
>
> > -----Original Message-----
> > From: Wisam Monther <wisamm@nvidia.com>
> > Sent: Tuesday, October 12, 2021 3:53 PM
> > To: Sean Zhang (Networking SW) <xiazhang@nvidia.com>; NBU-Contact-
> > Thomas Monjalon <thomas@monjalon.net>
> > Cc: dev@dpdk.org; Raslan Darawsheh <rasland@nvidia.com>
> > Subject: RE: [PATCH] app/flow-perf: add destination ports parameter
> >
> > Hi,
> >
> > > -----Original Message-----
> > > From: Sean Zhang (Networking SW) <xiazhang@nvidia.com>
> > > Sent: Tuesday, October 12, 2021 6:43 AM
> > > To: NBU-Contact-Thomas Monjalon <thomas@monjalon.net>; Wisam
> > Monther
> > > <wisamm@nvidia.com>
> > > Cc: dev@dpdk.org; Raslan Darawsheh <rasland@nvidia.com>
> > > Subject: [PATCH] app/flow-perf: add destination ports parameter
> > >
> > > Add destination ports(dst-ports) parameter for port-id action, the
> > > parameter is only valid for port-id action. The parameter is not
> > > Must, and the value is 1 by default as before if not provided.
> > >
> > > For example:
> > >
> > > $ dpdk-test-flow-perf -w 08:00.0,representor=[0,1] -- --transfer \
> > > > --ingress --transfer --ether --portmask=0x2 --vxlan-encap \
> > > > --port-id
> > > > --dst-ports=0
> > >
> > > This command means the rule created on representor 0 with port 0 as
> > > destination, since the portmask is 0x2 and dst-ports is 0:
> > >
> > > $ dpdk-test-flow-perf -w 08:00.0,representor=[0,1] \
> > > > -w 08:00.1,representor=[0,1]-- --transfer --ingress --transfer \
> > > > --ether --portmask=0x12 --vxlan-encap --port-id --dst-ports=0,3
> > >
> > > This command means the rules created on both representor 0 of PF 0
> > > and PF 1, the destination port for the first represontor is PF 0,
> > > and the destination port for the other one it PF 1.
> > >
> > > Signed-off-by: Sean Zhang <xiazhang@nvidia.com>
> >
> > Do you think it's applicable to use the same option?
> > I mean, usage:
> > --port-id: means default.
> > --port-id=N,M: use the parsing ports?
>
> Yes, since the argument can be optional, your suggestion is applicable. So do
> you suggest to change to --port-id=N,M?
Yes after 2end look, it make more sense to remove the dependency of two options for same action.
>
> >
> > BRs,
> > Wisam Jaddo
^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [dpdk-dev] [PATCH] app/flow-perf: add destination ports parameter
2021-10-12 8:15 ` Wisam Monther
@ 2021-10-12 8:22 ` Sean Zhang (Networking SW)
0 siblings, 0 replies; 14+ messages in thread
From: Sean Zhang (Networking SW) @ 2021-10-12 8:22 UTC (permalink / raw)
To: Wisam Monther, NBU-Contact-Thomas Monjalon; +Cc: dev, Raslan Darawsheh
> -----Original Message-----
> From: Wisam Monther <wisamm@nvidia.com>
> Sent: Tuesday, October 12, 2021 4:16 PM
> To: Sean Zhang (Networking SW) <xiazhang@nvidia.com>; NBU-Contact-
> Thomas Monjalon <thomas@monjalon.net>
> Cc: dev@dpdk.org; Raslan Darawsheh <rasland@nvidia.com>
> Subject: RE: [PATCH] app/flow-perf: add destination ports parameter
>
>
>
> > -----Original Message-----
> > From: Sean Zhang (Networking SW) <xiazhang@nvidia.com>
> > Sent: Tuesday, October 12, 2021 11:14 AM
> > To: Wisam Monther <wisamm@nvidia.com>; NBU-Contact-Thomas
> Monjalon
> > <thomas@monjalon.net>
> > Cc: dev@dpdk.org; Raslan Darawsheh <rasland@nvidia.com>
> > Subject: RE: [PATCH] app/flow-perf: add destination ports parameter
> >
> > Hi Wisam,
> >
> > > -----Original Message-----
> > > From: Wisam Monther <wisamm@nvidia.com>
> > > Sent: Tuesday, October 12, 2021 3:53 PM
> > > To: Sean Zhang (Networking SW) <xiazhang@nvidia.com>; NBU-Contact-
> > > Thomas Monjalon <thomas@monjalon.net>
> > > Cc: dev@dpdk.org; Raslan Darawsheh <rasland@nvidia.com>
> > > Subject: RE: [PATCH] app/flow-perf: add destination ports parameter
> > >
> > > Hi,
> > >
> > > > -----Original Message-----
> > > > From: Sean Zhang (Networking SW) <xiazhang@nvidia.com>
> > > > Sent: Tuesday, October 12, 2021 6:43 AM
> > > > To: NBU-Contact-Thomas Monjalon <thomas@monjalon.net>; Wisam
> > > Monther
> > > > <wisamm@nvidia.com>
> > > > Cc: dev@dpdk.org; Raslan Darawsheh <rasland@nvidia.com>
> > > > Subject: [PATCH] app/flow-perf: add destination ports parameter
> > > >
> > > > Add destination ports(dst-ports) parameter for port-id action, the
> > > > parameter is only valid for port-id action. The parameter is not
> > > > Must, and the value is 1 by default as before if not provided.
> > > >
> > > > For example:
> > > >
> > > > $ dpdk-test-flow-perf -w 08:00.0,representor=[0,1] -- --transfer \
> > > > > --ingress --transfer --ether --portmask=0x2 --vxlan-encap \
> > > > > --port-id
> > > > > --dst-ports=0
> > > >
> > > > This command means the rule created on representor 0 with port 0
> > > > as destination, since the portmask is 0x2 and dst-ports is 0:
> > > >
> > > > $ dpdk-test-flow-perf -w 08:00.0,representor=[0,1] \
> > > > > -w 08:00.1,representor=[0,1]-- --transfer --ingress --transfer \
> > > > > --ether --portmask=0x12 --vxlan-encap --port-id --dst-ports=0,3
> > > >
> > > > This command means the rules created on both representor 0 of PF 0
> > > > and PF 1, the destination port for the first represontor is PF 0,
> > > > and the destination port for the other one it PF 1.
> > > >
> > > > Signed-off-by: Sean Zhang <xiazhang@nvidia.com>
> > >
> > > Do you think it's applicable to use the same option?
> > > I mean, usage:
> > > --port-id: means default.
> > > --port-id=N,M: use the parsing ports?
> >
> > Yes, since the argument can be optional, your suggestion is
> > applicable. So do you suggest to change to --port-id=N,M?
>
> Yes after 2end look, it make more sense to remove the dependency of two
> options for same action.
OK, I will update the patch.
Thanks,
Sean
>
> >
> > >
> > > BRs,
> > > Wisam Jaddo
^ permalink raw reply [flat|nested] 14+ messages in thread
* [dpdk-dev] [V2] app/flow-perf: add destination ports parameter
2021-10-12 3:42 [dpdk-dev] [PATCH] app/flow-perf: add destination ports parameter Sean Zhang
2021-10-12 7:10 ` Wisam Monther
2021-10-12 7:53 ` Wisam Monther
@ 2021-10-13 7:44 ` Sean Zhang
2021-10-14 7:53 ` Wisam Monther
2021-10-28 3:57 ` [dpdk-dev] [PATCH] " Sean Zhang
` (2 subsequent siblings)
5 siblings, 1 reply; 14+ messages in thread
From: Sean Zhang @ 2021-10-13 7:44 UTC (permalink / raw)
To: thomas, Wisam Jaddo; +Cc: dev, rasland
Add optional destination ports parameter for port-id action.
The parameter is not must, and the value is 1 by default as before
if the parameter not provided.
For example:
$ dpdk-test-flow-perf -w 08:00.0,representor=[0,1] -- --transfer \
> --ingress --transfer --ether --portmask=0x2 --vxlan-encap \
> --port-id=0
This command means the rule created on representor 0 with port 0
as destination, since the portmask is 0x2 and dst-ports is 0:
$ dpdk-test-flow-perf -w 08:00.0,representor=[0,1] \
> -w 08:00.1,representor=[0,1]-- --transfer --ingress --transfer \
> --ether --portmask=0x12 --vxlan-encap --port-id=0,3
This command means the rules created on both representor 0 of PF 0
and PF 1, the destination port for the first represontor is PF 0,
and the destination port for the other one it PF 1.
Signed-off-by: Sean Zhang <xiazhang@nvidia.com>
---
v2:
remove new added dst-ports parameter, reuse port-id with optional
parameter
---
---
app/test-flow-perf/actions_gen.c | 7 +++++--
app/test-flow-perf/actions_gen.h | 2 +-
app/test-flow-perf/flow_gen.c | 3 ++-
app/test-flow-perf/flow_gen.h | 1 +
app/test-flow-perf/main.c | 29 +++++++++++++++++++++++------
doc/guides/tools/flow-perf.rst | 3 +++
6 files changed, 35 insertions(+), 10 deletions(-)
diff --git a/app/test-flow-perf/actions_gen.c b/app/test-flow-perf/actions_gen.c
index 82cddfc676..8786dc967c 100644
--- a/app/test-flow-perf/actions_gen.c
+++ b/app/test-flow-perf/actions_gen.c
@@ -29,6 +29,7 @@ struct additional_para {
uint32_t counter;
uint64_t encap_data;
uint64_t decap_data;
+ uint16_t dst_port;
uint8_t core_idx;
bool unique_data;
};
@@ -171,12 +172,13 @@ add_set_tag(struct rte_flow_action *actions,
static void
add_port_id(struct rte_flow_action *actions,
uint8_t actions_counter,
- __rte_unused struct additional_para para)
+ struct additional_para para)
{
static struct rte_flow_action_port_id port_id = {
.id = PORT_ID_DST,
};
+ port_id.id = para.dst_port;
actions[actions_counter].type = RTE_FLOW_ACTION_TYPE_PORT_ID;
actions[actions_counter].conf = &port_id;
}
@@ -909,7 +911,7 @@ void
fill_actions(struct rte_flow_action *actions, uint64_t *flow_actions,
uint32_t counter, uint16_t next_table, uint16_t hairpinq,
uint64_t encap_data, uint64_t decap_data, uint8_t core_idx,
- bool unique_data)
+ bool unique_data, uint16_t dst_port)
{
struct additional_para additional_para_data;
uint8_t actions_counter = 0;
@@ -933,6 +935,7 @@ fill_actions(struct rte_flow_action *actions, uint64_t *flow_actions,
.decap_data = decap_data,
.core_idx = core_idx,
.unique_data = unique_data,
+ .dst_port = dst_port,
};
if (hairpinq != 0) {
diff --git a/app/test-flow-perf/actions_gen.h b/app/test-flow-perf/actions_gen.h
index 6f2f833496..f3bb6fec41 100644
--- a/app/test-flow-perf/actions_gen.h
+++ b/app/test-flow-perf/actions_gen.h
@@ -20,6 +20,6 @@
void fill_actions(struct rte_flow_action *actions, uint64_t *flow_actions,
uint32_t counter, uint16_t next_table, uint16_t hairpinq,
uint64_t encap_data, uint64_t decap_data, uint8_t core_idx,
- bool unique_data);
+ bool unique_data, uint16_t dst_port);
#endif /* FLOW_PERF_ACTION_GEN */
diff --git a/app/test-flow-perf/flow_gen.c b/app/test-flow-perf/flow_gen.c
index 8f87fac5f6..890387bffa 100644
--- a/app/test-flow-perf/flow_gen.c
+++ b/app/test-flow-perf/flow_gen.c
@@ -45,6 +45,7 @@ generate_flow(uint16_t port_id,
uint16_t hairpinq,
uint64_t encap_data,
uint64_t decap_data,
+ uint16_t dst_port,
uint8_t core_idx,
bool unique_data,
struct rte_flow_error *error)
@@ -63,7 +64,7 @@ generate_flow(uint16_t port_id,
fill_actions(actions, flow_actions,
outer_ip_src, next_table, hairpinq,
encap_data, decap_data, core_idx,
- unique_data);
+ unique_data, dst_port);
fill_items(items, flow_items, outer_ip_src, core_idx);
diff --git a/app/test-flow-perf/flow_gen.h b/app/test-flow-perf/flow_gen.h
index dc887fceae..2daebbe493 100644
--- a/app/test-flow-perf/flow_gen.h
+++ b/app/test-flow-perf/flow_gen.h
@@ -34,6 +34,7 @@ generate_flow(uint16_t port_id,
uint16_t hairpinq,
uint64_t encap_data,
uint64_t decap_data,
+ uint16_t dst_port,
uint8_t core_idx,
bool unique_data,
struct rte_flow_error *error);
diff --git a/app/test-flow-perf/main.c b/app/test-flow-perf/main.c
index 9be8edc31d..5d12bfeb03 100644
--- a/app/test-flow-perf/main.c
+++ b/app/test-flow-perf/main.c
@@ -56,6 +56,7 @@ static uint64_t flow_attrs[MAX_ATTRS_NUM];
static uint8_t items_idx, actions_idx, attrs_idx;
static uint64_t ports_mask;
+static uint16_t dst_ports[RTE_MAX_ETHPORTS];
static volatile bool force_quit;
static bool dump_iterations;
static bool delete_flag;
@@ -595,7 +596,7 @@ args_parse(int argc, char **argv)
{ "icmpv4", 0, 0, 0 },
{ "icmpv6", 0, 0, 0 },
/* Actions */
- { "port-id", 0, 0, 0 },
+ { "port-id", 2, 0, 0 },
{ "rss", 0, 0, 0 },
{ "queue", 0, 0, 0 },
{ "jump", 0, 0, 0 },
@@ -633,6 +634,9 @@ args_parse(int argc, char **argv)
RTE_ETH_FOREACH_DEV(i)
ports_mask |= 1 << i;
+ for (i = 0; i < RTE_MAX_ETHPORTS; i++)
+ dst_ports[i] = PORT_ID_DST;
+
hairpin_queues_num = 0;
argvopt = argv;
@@ -787,6 +791,17 @@ args_parse(int argc, char **argv)
rte_exit(EXIT_FAILURE, "Invalid fwd port mask\n");
ports_mask = pm;
}
+ if (strcmp(lgopts[opt_idx].name,
+ "port-id") == 0) {
+ uint16_t port_idx = 0;
+ char *token;
+
+ token = strtok(optarg, ",");
+ while (token != NULL) {
+ dst_ports[port_idx++] = atoi(token);
+ token = strtok(NULL, ",");
+ }
+ }
if (strcmp(lgopts[opt_idx].name, "cores") == 0) {
n = atoi(optarg);
if ((int) rte_lcore_count() <= n) {
@@ -1128,7 +1143,7 @@ destroy_flows(int port_id, uint8_t core_id, struct rte_flow **flows_list)
}
static struct rte_flow **
-insert_flows(int port_id, uint8_t core_id)
+insert_flows(int port_id, uint8_t core_id, uint16_t dst_port_id)
{
struct rte_flow **flows_list;
struct rte_flow_error error;
@@ -1173,8 +1188,8 @@ insert_flows(int port_id, uint8_t core_id)
* group 0 eth / end actions jump group <flow_group>
*/
flow = generate_flow(port_id, 0, flow_attrs,
- global_items, global_actions,
- flow_group, 0, 0, 0, 0, core_id, unique_data, &error);
+ global_items, global_actions, flow_group, 0, 0, 0, 0,
+ dst_port_id, core_id, unique_data, &error);
if (flow == NULL) {
print_flow_error(error);
@@ -1189,7 +1204,7 @@ insert_flows(int port_id, uint8_t core_id)
flow_attrs, flow_items, flow_actions,
JUMP_ACTION_TABLE, counter,
hairpin_queues_num,
- encap_data, decap_data,
+ encap_data, decap_data, dst_port_id,
core_id, unique_data, &error);
if (!counter) {
@@ -1250,6 +1265,7 @@ static void
flows_handler(uint8_t core_id)
{
struct rte_flow **flows_list;
+ uint16_t port_idx = 0;
uint16_t nr_ports;
int port_id;
@@ -1269,7 +1285,8 @@ flows_handler(uint8_t core_id)
mc_pool.last_alloc[core_id] = (int64_t)dump_socket_mem(stdout);
if (has_meter())
meters_handler(port_id, core_id, METER_CREATE);
- flows_list = insert_flows(port_id, core_id);
+ flows_list = insert_flows(port_id, core_id,
+ dst_ports[port_idx++]);
if (flows_list == NULL)
rte_exit(EXIT_FAILURE, "Error: Insertion Failed!\n");
mc_pool.current_alloc[core_id] = (int64_t)dump_socket_mem(stdout);
diff --git a/doc/guides/tools/flow-perf.rst b/doc/guides/tools/flow-perf.rst
index 280bf7e0e0..edfd81c25f 100644
--- a/doc/guides/tools/flow-perf.rst
+++ b/doc/guides/tools/flow-perf.rst
@@ -205,6 +205,9 @@ Actions:
Add port redirection action to all flows actions.
Port redirection destination is defined in user_parameters.h
under PORT_ID_DST, default value = 1.
+ It can also has optional parameter like --port-id=N[,M] to
+ specify the destination port, the number of values should be
+ the same with number of set bits in portmask.
* ``--rss``
Add RSS action to all flows actions,
--
2.33.0
^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [dpdk-dev] [V2] app/flow-perf: add destination ports parameter
2021-10-13 7:44 ` [dpdk-dev] [V2] " Sean Zhang
@ 2021-10-14 7:53 ` Wisam Monther
2021-10-25 19:40 ` Thomas Monjalon
0 siblings, 1 reply; 14+ messages in thread
From: Wisam Monther @ 2021-10-14 7:53 UTC (permalink / raw)
To: Sean Zhang (Networking SW), NBU-Contact-Thomas Monjalon
Cc: dev, Raslan Darawsheh
Hi Sean,
> -----Original Message-----
> From: Sean Zhang (Networking SW) <xiazhang@nvidia.com>
> Sent: Wednesday, October 13, 2021 10:44 AM
> To: NBU-Contact-Thomas Monjalon <thomas@monjalon.net>; Wisam
> Monther <wisamm@nvidia.com>
> Cc: dev@dpdk.org; Raslan Darawsheh <rasland@nvidia.com>
> Subject: [V2] app/flow-perf: add destination ports parameter
>
> Add optional destination ports parameter for port-id action.
> The parameter is not must, and the value is 1 by default as before if the
> parameter not provided.
>
> For example:
>
> $ dpdk-test-flow-perf -w 08:00.0,representor=[0,1] -- --transfer \
> > --ingress --transfer --ether --portmask=0x2 --vxlan-encap \
> > --port-id=0
>
> This command means the rule created on representor 0 with port 0 as
> destination, since the portmask is 0x2 and dst-ports is 0:
>
> $ dpdk-test-flow-perf -w 08:00.0,representor=[0,1] \
> > -w 08:00.1,representor=[0,1]-- --transfer --ingress --transfer \
> > --ether --portmask=0x12 --vxlan-encap --port-id=0,3
>
> This command means the rules created on both representor 0 of PF 0 and PF
> 1, the destination port for the first represontor is PF 0, and the destination
> port for the other one it PF 1.
>
> Signed-off-by: Sean Zhang <xiazhang@nvidia.com>
> ---
> v2:
> remove new added dst-ports parameter, reuse port-id with optional
> parameter
> ---
Reviewed-by: Wisam Jaddo <wisamm@nvidia.com>
BRs,
Wisam Jaddo
^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [dpdk-dev] [V2] app/flow-perf: add destination ports parameter
2021-10-14 7:53 ` Wisam Monther
@ 2021-10-25 19:40 ` Thomas Monjalon
0 siblings, 0 replies; 14+ messages in thread
From: Thomas Monjalon @ 2021-10-25 19:40 UTC (permalink / raw)
To: Sean Zhang (Networking SW); +Cc: dev, Raslan Darawsheh, Wisam Monther
> > Add optional destination ports parameter for port-id action.
> > The parameter is not must, and the value is 1 by default as before if the
> > parameter not provided.
> >
> > For example:
> >
> > $ dpdk-test-flow-perf -w 08:00.0,representor=[0,1] -- --transfer \
> > > --ingress --transfer --ether --portmask=0x2 --vxlan-encap \
> > > --port-id=0
> >
> > This command means the rule created on representor 0 with port 0 as
> > destination, since the portmask is 0x2 and dst-ports is 0:
> >
> > $ dpdk-test-flow-perf -w 08:00.0,representor=[0,1] \
> > > -w 08:00.1,representor=[0,1]-- --transfer --ingress --transfer \
> > > --ether --portmask=0x12 --vxlan-encap --port-id=0,3
> >
> > This command means the rules created on both representor 0 of PF 0 and PF
> > 1, the destination port for the first represontor is PF 0, and the destination
> > port for the other one it PF 1.
> >
> > Signed-off-by: Sean Zhang <xiazhang@nvidia.com>
>
> Reviewed-by: Wisam Jaddo <wisamm@nvidia.com>
It conflicts with Wisam's patch adding more options.
Please rebase.
^ permalink raw reply [flat|nested] 14+ messages in thread
* [dpdk-dev] [PATCH] app/flow-perf: add destination ports parameter
2021-10-12 3:42 [dpdk-dev] [PATCH] app/flow-perf: add destination ports parameter Sean Zhang
` (2 preceding siblings ...)
2021-10-13 7:44 ` [dpdk-dev] [V2] " Sean Zhang
@ 2021-10-28 3:57 ` Sean Zhang
2021-10-28 4:01 ` [dpdk-dev] [V3] " Sean Zhang
2021-10-29 5:52 ` Sean Zhang
5 siblings, 0 replies; 14+ messages in thread
From: Sean Zhang @ 2021-10-28 3:57 UTC (permalink / raw)
To: thomas, Wisam Jaddo; +Cc: dev, rasland
Add optional destination ports parameter for port-id action.
The parameter is not must, and the value is 1 by default as before
if the parameter not provided.
For example:
$ dpdk-test-flow-perf -w 08:00.0,representor=[0,1] -- --transfer \
> --ingress --transfer --ether --portmask=0x2 --vxlan-encap \
> --port-id=0
This command means the rule created on representor 0 with port 0
as destination, since the portmask is 0x2 and dst-ports is 0:
$ dpdk-test-flow-perf -w 08:00.0,representor=[0,1] \
> -w 08:00.1,representor=[0,1]-- --transfer --ingress --transfer \
> --ether --portmask=0x12 --vxlan-encap --port-id=0,3
This command means the rules created on both representor 0 of PF 0
and PF 1, the destination port for the first represontor is PF 0,
and the destination port for the other one it PF 1.
Signed-off-by: Sean Zhang <xiazhang@nvidia.com>
---
v3:
resolve merging conflict
v2:
remove new added dst-ports parameter, reuse port-id with optional
parameter
---
---
app/test-flow-perf/actions_gen.c | 7 +++++--
app/test-flow-perf/actions_gen.h | 2 +-
app/test-flow-perf/flow_gen.c | 3 ++-
app/test-flow-perf/flow_gen.h | 1 +
app/test-flow-perf/main.c | 31 ++++++++++++++++++++++++-------
doc/guides/tools/flow-perf.rst | 3 +++
6 files changed, 36 insertions(+), 11 deletions(-)
diff --git a/app/test-flow-perf/actions_gen.c b/app/test-flow-perf/actions_gen.c
index 7c209f7266..13e1b82389 100644
--- a/app/test-flow-perf/actions_gen.c
+++ b/app/test-flow-perf/actions_gen.c
@@ -29,6 +29,7 @@ struct additional_para {
uint32_t counter;
uint64_t encap_data;
uint64_t decap_data;
+ uint16_t dst_port;
uint8_t core_idx;
bool unique_data;
};
@@ -171,12 +172,13 @@ add_set_tag(struct rte_flow_action *actions,
static void
add_port_id(struct rte_flow_action *actions,
uint8_t actions_counter,
- __rte_unused struct additional_para para)
+ struct additional_para para)
{
static struct rte_flow_action_port_id port_id = {
.id = PORT_ID_DST,
};
+ port_id.id = para.dst_port;
actions[actions_counter].type = RTE_FLOW_ACTION_TYPE_PORT_ID;
actions[actions_counter].conf = &port_id;
}
@@ -909,7 +911,7 @@ void
fill_actions(struct rte_flow_action *actions, uint64_t *flow_actions,
uint32_t counter, uint16_t next_table, uint16_t hairpinq,
uint64_t encap_data, uint64_t decap_data, uint8_t core_idx,
- bool unique_data, uint8_t rx_queues_count)
+ bool unique_data, uint8_t rx_queues_count, uint16_t dst_port)
{
struct additional_para additional_para_data;
uint8_t actions_counter = 0;
@@ -933,6 +935,7 @@ fill_actions(struct rte_flow_action *actions, uint64_t *flow_actions,
.decap_data = decap_data,
.core_idx = core_idx,
.unique_data = unique_data,
+ .dst_port = dst_port,
};
if (hairpinq != 0) {
diff --git a/app/test-flow-perf/actions_gen.h b/app/test-flow-perf/actions_gen.h
index 8990686269..9e13b164f9 100644
--- a/app/test-flow-perf/actions_gen.h
+++ b/app/test-flow-perf/actions_gen.h
@@ -20,6 +20,6 @@
void fill_actions(struct rte_flow_action *actions, uint64_t *flow_actions,
uint32_t counter, uint16_t next_table, uint16_t hairpinq,
uint64_t encap_data, uint64_t decap_data, uint8_t core_idx,
- bool unique_data, uint8_t rx_queues_count);
+ bool unique_data, uint8_t rx_queues_count, uint16_t dst_port);
#endif /* FLOW_PERF_ACTION_GEN */
diff --git a/app/test-flow-perf/flow_gen.c b/app/test-flow-perf/flow_gen.c
index 51871dbfdc..c7b7652c02 100644
--- a/app/test-flow-perf/flow_gen.c
+++ b/app/test-flow-perf/flow_gen.c
@@ -45,6 +45,7 @@ generate_flow(uint16_t port_id,
uint16_t hairpinq,
uint64_t encap_data,
uint64_t decap_data,
+ uint16_t dst_port,
uint8_t core_idx,
uint8_t rx_queues_count,
bool unique_data,
@@ -64,7 +65,7 @@ generate_flow(uint16_t port_id,
fill_actions(actions, flow_actions,
outer_ip_src, next_table, hairpinq,
encap_data, decap_data, core_idx,
- unique_data, rx_queues_count);
+ unique_data, rx_queues_count, dst_port);
fill_items(items, flow_items, outer_ip_src, core_idx);
diff --git a/app/test-flow-perf/flow_gen.h b/app/test-flow-perf/flow_gen.h
index 1118a9fc14..46ce575ff8 100644
--- a/app/test-flow-perf/flow_gen.h
+++ b/app/test-flow-perf/flow_gen.h
@@ -34,6 +34,7 @@ generate_flow(uint16_t port_id,
uint16_t hairpinq,
uint64_t encap_data,
uint64_t decap_data,
+ uint16_t dst_port,
uint8_t core_idx,
uint8_t rx_queues_count,
bool unique_data,
diff --git a/app/test-flow-perf/main.c b/app/test-flow-perf/main.c
index 3ebc025fb2..c1ad9bb0a3 100644
--- a/app/test-flow-perf/main.c
+++ b/app/test-flow-perf/main.c
@@ -56,6 +56,7 @@ static uint64_t flow_attrs[MAX_ATTRS_NUM];
static uint8_t items_idx, actions_idx, attrs_idx;
static uint64_t ports_mask;
+static uint16_t dst_ports[RTE_MAX_ETHPORTS];
static volatile bool force_quit;
static bool dump_iterations;
static bool delete_flag;
@@ -619,7 +620,7 @@ args_parse(int argc, char **argv)
{ "icmpv4", 0, 0, 0 },
{ "icmpv6", 0, 0, 0 },
/* Actions */
- { "port-id", 0, 0, 0 },
+ { "port-id", 2, 0, 0 },
{ "rss", 0, 0, 0 },
{ "queue", 0, 0, 0 },
{ "jump", 0, 0, 0 },
@@ -657,6 +658,9 @@ args_parse(int argc, char **argv)
RTE_ETH_FOREACH_DEV(i)
ports_mask |= 1 << i;
+ for (i = 0; i < RTE_MAX_ETHPORTS; i++)
+ dst_ports[i] = PORT_ID_DST;
+
hairpin_queues_num = 0;
argvopt = argv;
@@ -811,6 +815,17 @@ args_parse(int argc, char **argv)
rte_exit(EXIT_FAILURE, "Invalid fwd port mask\n");
ports_mask = pm;
}
+ if (strcmp(lgopts[opt_idx].name,
+ "port-id") == 0) {
+ uint16_t port_idx = 0;
+ char *token;
+
+ token = strtok(optarg, ",");
+ while (token != NULL) {
+ dst_ports[port_idx++] = atoi(token);
+ token = strtok(NULL, ",");
+ }
+ }
if (strcmp(lgopts[opt_idx].name, "rxq") == 0) {
n = atoi(optarg);
rx_queues_count = (uint8_t) n;
@@ -1180,7 +1195,7 @@ destroy_flows(int port_id, uint8_t core_id, struct rte_flow **flows_list)
}
static struct rte_flow **
-insert_flows(int port_id, uint8_t core_id)
+insert_flows(int port_id, uint8_t core_id, uint16_t dst_port_id)
{
struct rte_flow **flows_list;
struct rte_flow_error error;
@@ -1226,8 +1241,8 @@ insert_flows(int port_id, uint8_t core_id)
*/
flow = generate_flow(port_id, 0, flow_attrs,
global_items, global_actions,
- flow_group, 0, 0, 0, 0, core_id, rx_queues_count,
- unique_data, &error);
+ flow_group, 0, 0, 0, 0, dst_port_id, core_id,
+ rx_queues_count, unique_data, &error);
if (flow == NULL) {
print_flow_error(error);
@@ -1241,8 +1256,8 @@ insert_flows(int port_id, uint8_t core_id)
flow = generate_flow(port_id, flow_group,
flow_attrs, flow_items, flow_actions,
JUMP_ACTION_TABLE, counter,
- hairpin_queues_num,
- encap_data, decap_data,
+ hairpin_queues_num, encap_data,
+ decap_data, dst_port_id,
core_id, rx_queues_count,
unique_data, &error);
@@ -1304,6 +1319,7 @@ static void
flows_handler(uint8_t core_id)
{
struct rte_flow **flows_list;
+ uint16_t port_idx = 0;
uint16_t nr_ports;
int port_id;
@@ -1323,7 +1339,8 @@ flows_handler(uint8_t core_id)
mc_pool.last_alloc[core_id] = (int64_t)dump_socket_mem(stdout);
if (has_meter())
meters_handler(port_id, core_id, METER_CREATE);
- flows_list = insert_flows(port_id, core_id);
+ flows_list = insert_flows(port_id, core_id,
+ dst_ports[port_idx++]);
if (flows_list == NULL)
rte_exit(EXIT_FAILURE, "Error: Insertion Failed!\n");
mc_pool.current_alloc[core_id] = (int64_t)dump_socket_mem(stdout);
diff --git a/doc/guides/tools/flow-perf.rst b/doc/guides/tools/flow-perf.rst
index 0855f88689..9812b43a74 100644
--- a/doc/guides/tools/flow-perf.rst
+++ b/doc/guides/tools/flow-perf.rst
@@ -230,6 +230,9 @@ Actions:
Add port redirection action to all flows actions.
Port redirection destination is defined in user_parameters.h
under PORT_ID_DST, default value = 1.
+ It can also has optional parameter like --port-id=N[,M] to
+ specify the destination port, the number of values should be
+ the same with number of set bits in portmask.
* ``--rss``
Add RSS action to all flows actions,
--
2.33.0
^ permalink raw reply [flat|nested] 14+ messages in thread
* [dpdk-dev] [V3] app/flow-perf: add destination ports parameter
2021-10-12 3:42 [dpdk-dev] [PATCH] app/flow-perf: add destination ports parameter Sean Zhang
` (3 preceding siblings ...)
2021-10-28 3:57 ` [dpdk-dev] [PATCH] " Sean Zhang
@ 2021-10-28 4:01 ` Sean Zhang
2021-10-29 5:52 ` Sean Zhang
5 siblings, 0 replies; 14+ messages in thread
From: Sean Zhang @ 2021-10-28 4:01 UTC (permalink / raw)
To: thomas, Wisam Jaddo; +Cc: dev, rasland
Add optional destination ports parameter for port-id action.
The parameter is not must, and the value is 1 by default as before
if the parameter not provided.
For example:
$ dpdk-test-flow-perf -w 08:00.0,representor=[0,1] -- --transfer \
> --ingress --transfer --ether --portmask=0x2 --vxlan-encap \
> --port-id=0
This command means the rule created on representor 0 with port 0
as destination, since the portmask is 0x2 and dst-ports is 0:
$ dpdk-test-flow-perf -w 08:00.0,representor=[0,1] \
> -w 08:00.1,representor=[0,1]-- --transfer --ingress --transfer \
> --ether --portmask=0x12 --vxlan-encap --port-id=0,3
This command means the rules created on both representor 0 of PF 0
and PF 1, the destination port for the first represontor is PF 0,
and the destination port for the other one it PF 1.
Signed-off-by: Sean Zhang <xiazhang@nvidia.com>
---
v3:
resolve merging conflict
v2:
remove new added dst-ports parameter, reuse port-id with optional
parameter
---
---
app/test-flow-perf/actions_gen.c | 7 +++++--
app/test-flow-perf/actions_gen.h | 2 +-
app/test-flow-perf/flow_gen.c | 3 ++-
app/test-flow-perf/flow_gen.h | 1 +
app/test-flow-perf/main.c | 31 ++++++++++++++++++++++++-------
doc/guides/tools/flow-perf.rst | 3 +++
6 files changed, 36 insertions(+), 11 deletions(-)
diff --git a/app/test-flow-perf/actions_gen.c b/app/test-flow-perf/actions_gen.c
index 7c209f7266..13e1b82389 100644
--- a/app/test-flow-perf/actions_gen.c
+++ b/app/test-flow-perf/actions_gen.c
@@ -29,6 +29,7 @@ struct additional_para {
uint32_t counter;
uint64_t encap_data;
uint64_t decap_data;
+ uint16_t dst_port;
uint8_t core_idx;
bool unique_data;
};
@@ -171,12 +172,13 @@ add_set_tag(struct rte_flow_action *actions,
static void
add_port_id(struct rte_flow_action *actions,
uint8_t actions_counter,
- __rte_unused struct additional_para para)
+ struct additional_para para)
{
static struct rte_flow_action_port_id port_id = {
.id = PORT_ID_DST,
};
+ port_id.id = para.dst_port;
actions[actions_counter].type = RTE_FLOW_ACTION_TYPE_PORT_ID;
actions[actions_counter].conf = &port_id;
}
@@ -909,7 +911,7 @@ void
fill_actions(struct rte_flow_action *actions, uint64_t *flow_actions,
uint32_t counter, uint16_t next_table, uint16_t hairpinq,
uint64_t encap_data, uint64_t decap_data, uint8_t core_idx,
- bool unique_data, uint8_t rx_queues_count)
+ bool unique_data, uint8_t rx_queues_count, uint16_t dst_port)
{
struct additional_para additional_para_data;
uint8_t actions_counter = 0;
@@ -933,6 +935,7 @@ fill_actions(struct rte_flow_action *actions, uint64_t *flow_actions,
.decap_data = decap_data,
.core_idx = core_idx,
.unique_data = unique_data,
+ .dst_port = dst_port,
};
if (hairpinq != 0) {
diff --git a/app/test-flow-perf/actions_gen.h b/app/test-flow-perf/actions_gen.h
index 8990686269..9e13b164f9 100644
--- a/app/test-flow-perf/actions_gen.h
+++ b/app/test-flow-perf/actions_gen.h
@@ -20,6 +20,6 @@
void fill_actions(struct rte_flow_action *actions, uint64_t *flow_actions,
uint32_t counter, uint16_t next_table, uint16_t hairpinq,
uint64_t encap_data, uint64_t decap_data, uint8_t core_idx,
- bool unique_data, uint8_t rx_queues_count);
+ bool unique_data, uint8_t rx_queues_count, uint16_t dst_port);
#endif /* FLOW_PERF_ACTION_GEN */
diff --git a/app/test-flow-perf/flow_gen.c b/app/test-flow-perf/flow_gen.c
index 51871dbfdc..c7b7652c02 100644
--- a/app/test-flow-perf/flow_gen.c
+++ b/app/test-flow-perf/flow_gen.c
@@ -45,6 +45,7 @@ generate_flow(uint16_t port_id,
uint16_t hairpinq,
uint64_t encap_data,
uint64_t decap_data,
+ uint16_t dst_port,
uint8_t core_idx,
uint8_t rx_queues_count,
bool unique_data,
@@ -64,7 +65,7 @@ generate_flow(uint16_t port_id,
fill_actions(actions, flow_actions,
outer_ip_src, next_table, hairpinq,
encap_data, decap_data, core_idx,
- unique_data, rx_queues_count);
+ unique_data, rx_queues_count, dst_port);
fill_items(items, flow_items, outer_ip_src, core_idx);
diff --git a/app/test-flow-perf/flow_gen.h b/app/test-flow-perf/flow_gen.h
index 1118a9fc14..46ce575ff8 100644
--- a/app/test-flow-perf/flow_gen.h
+++ b/app/test-flow-perf/flow_gen.h
@@ -34,6 +34,7 @@ generate_flow(uint16_t port_id,
uint16_t hairpinq,
uint64_t encap_data,
uint64_t decap_data,
+ uint16_t dst_port,
uint8_t core_idx,
uint8_t rx_queues_count,
bool unique_data,
diff --git a/app/test-flow-perf/main.c b/app/test-flow-perf/main.c
index 3ebc025fb2..c1ad9bb0a3 100644
--- a/app/test-flow-perf/main.c
+++ b/app/test-flow-perf/main.c
@@ -56,6 +56,7 @@ static uint64_t flow_attrs[MAX_ATTRS_NUM];
static uint8_t items_idx, actions_idx, attrs_idx;
static uint64_t ports_mask;
+static uint16_t dst_ports[RTE_MAX_ETHPORTS];
static volatile bool force_quit;
static bool dump_iterations;
static bool delete_flag;
@@ -619,7 +620,7 @@ args_parse(int argc, char **argv)
{ "icmpv4", 0, 0, 0 },
{ "icmpv6", 0, 0, 0 },
/* Actions */
- { "port-id", 0, 0, 0 },
+ { "port-id", 2, 0, 0 },
{ "rss", 0, 0, 0 },
{ "queue", 0, 0, 0 },
{ "jump", 0, 0, 0 },
@@ -657,6 +658,9 @@ args_parse(int argc, char **argv)
RTE_ETH_FOREACH_DEV(i)
ports_mask |= 1 << i;
+ for (i = 0; i < RTE_MAX_ETHPORTS; i++)
+ dst_ports[i] = PORT_ID_DST;
+
hairpin_queues_num = 0;
argvopt = argv;
@@ -811,6 +815,17 @@ args_parse(int argc, char **argv)
rte_exit(EXIT_FAILURE, "Invalid fwd port mask\n");
ports_mask = pm;
}
+ if (strcmp(lgopts[opt_idx].name,
+ "port-id") == 0) {
+ uint16_t port_idx = 0;
+ char *token;
+
+ token = strtok(optarg, ",");
+ while (token != NULL) {
+ dst_ports[port_idx++] = atoi(token);
+ token = strtok(NULL, ",");
+ }
+ }
if (strcmp(lgopts[opt_idx].name, "rxq") == 0) {
n = atoi(optarg);
rx_queues_count = (uint8_t) n;
@@ -1180,7 +1195,7 @@ destroy_flows(int port_id, uint8_t core_id, struct rte_flow **flows_list)
}
static struct rte_flow **
-insert_flows(int port_id, uint8_t core_id)
+insert_flows(int port_id, uint8_t core_id, uint16_t dst_port_id)
{
struct rte_flow **flows_list;
struct rte_flow_error error;
@@ -1226,8 +1241,8 @@ insert_flows(int port_id, uint8_t core_id)
*/
flow = generate_flow(port_id, 0, flow_attrs,
global_items, global_actions,
- flow_group, 0, 0, 0, 0, core_id, rx_queues_count,
- unique_data, &error);
+ flow_group, 0, 0, 0, 0, dst_port_id, core_id,
+ rx_queues_count, unique_data, &error);
if (flow == NULL) {
print_flow_error(error);
@@ -1241,8 +1256,8 @@ insert_flows(int port_id, uint8_t core_id)
flow = generate_flow(port_id, flow_group,
flow_attrs, flow_items, flow_actions,
JUMP_ACTION_TABLE, counter,
- hairpin_queues_num,
- encap_data, decap_data,
+ hairpin_queues_num, encap_data,
+ decap_data, dst_port_id,
core_id, rx_queues_count,
unique_data, &error);
@@ -1304,6 +1319,7 @@ static void
flows_handler(uint8_t core_id)
{
struct rte_flow **flows_list;
+ uint16_t port_idx = 0;
uint16_t nr_ports;
int port_id;
@@ -1323,7 +1339,8 @@ flows_handler(uint8_t core_id)
mc_pool.last_alloc[core_id] = (int64_t)dump_socket_mem(stdout);
if (has_meter())
meters_handler(port_id, core_id, METER_CREATE);
- flows_list = insert_flows(port_id, core_id);
+ flows_list = insert_flows(port_id, core_id,
+ dst_ports[port_idx++]);
if (flows_list == NULL)
rte_exit(EXIT_FAILURE, "Error: Insertion Failed!\n");
mc_pool.current_alloc[core_id] = (int64_t)dump_socket_mem(stdout);
diff --git a/doc/guides/tools/flow-perf.rst b/doc/guides/tools/flow-perf.rst
index 0855f88689..9812b43a74 100644
--- a/doc/guides/tools/flow-perf.rst
+++ b/doc/guides/tools/flow-perf.rst
@@ -230,6 +230,9 @@ Actions:
Add port redirection action to all flows actions.
Port redirection destination is defined in user_parameters.h
under PORT_ID_DST, default value = 1.
+ It can also has optional parameter like --port-id=N[,M] to
+ specify the destination port, the number of values should be
+ the same with number of set bits in portmask.
* ``--rss``
Add RSS action to all flows actions,
--
2.33.0
^ permalink raw reply [flat|nested] 14+ messages in thread
* [dpdk-dev] [V3] app/flow-perf: add destination ports parameter
2021-10-12 3:42 [dpdk-dev] [PATCH] app/flow-perf: add destination ports parameter Sean Zhang
` (4 preceding siblings ...)
2021-10-28 4:01 ` [dpdk-dev] [V3] " Sean Zhang
@ 2021-10-29 5:52 ` Sean Zhang
2021-10-31 8:44 ` Wisam Monther
5 siblings, 1 reply; 14+ messages in thread
From: Sean Zhang @ 2021-10-29 5:52 UTC (permalink / raw)
To: thomas, Wisam Jaddo; +Cc: dev, rasland
Add optional destination ports parameter for port-id action.
The parameter is not must, and the value is 1 by default as before
if the parameter not provided.
For example:
$ dpdk-test-flow-perf -w 08:00.0,representor=[0,1] -- --transfer \
> --ingress --transfer --ether --portmask=0x2 --vxlan-encap \
> --port-id=0
This command means the rule created on representor 0 with port 0
as destination, since the portmask is 0x2 and dst-ports is 0:
$ dpdk-test-flow-perf -w 08:00.0,representor=[0,1] \
> -w 08:00.1,representor=[0,1]-- --transfer --ingress --transfer \
> --ether --portmask=0x12 --vxlan-encap --port-id=0,3
This command means the rules created on both representor 0 of PF 0
and PF 1, the destination port for the first represontor is PF 0,
and the destination port for the other one it PF 1.
Signed-off-by: Sean Zhang <xiazhang@nvidia.com>
---
v3:
resolve merging conflict
v2:
remove new added dst-ports parameter, reuse port-id with optional
parameter
---
---
app/test-flow-perf/actions_gen.c | 7 +++++--
app/test-flow-perf/actions_gen.h | 2 +-
app/test-flow-perf/flow_gen.c | 3 ++-
app/test-flow-perf/flow_gen.h | 1 +
app/test-flow-perf/main.c | 31 ++++++++++++++++++++++++-------
doc/guides/tools/flow-perf.rst | 4 ++++
6 files changed, 37 insertions(+), 11 deletions(-)
diff --git a/app/test-flow-perf/actions_gen.c b/app/test-flow-perf/actions_gen.c
index 7c209f7266..13e1b82389 100644
--- a/app/test-flow-perf/actions_gen.c
+++ b/app/test-flow-perf/actions_gen.c
@@ -29,6 +29,7 @@ struct additional_para {
uint32_t counter;
uint64_t encap_data;
uint64_t decap_data;
+ uint16_t dst_port;
uint8_t core_idx;
bool unique_data;
};
@@ -171,12 +172,13 @@ add_set_tag(struct rte_flow_action *actions,
static void
add_port_id(struct rte_flow_action *actions,
uint8_t actions_counter,
- __rte_unused struct additional_para para)
+ struct additional_para para)
{
static struct rte_flow_action_port_id port_id = {
.id = PORT_ID_DST,
};
+ port_id.id = para.dst_port;
actions[actions_counter].type = RTE_FLOW_ACTION_TYPE_PORT_ID;
actions[actions_counter].conf = &port_id;
}
@@ -909,7 +911,7 @@ void
fill_actions(struct rte_flow_action *actions, uint64_t *flow_actions,
uint32_t counter, uint16_t next_table, uint16_t hairpinq,
uint64_t encap_data, uint64_t decap_data, uint8_t core_idx,
- bool unique_data, uint8_t rx_queues_count)
+ bool unique_data, uint8_t rx_queues_count, uint16_t dst_port)
{
struct additional_para additional_para_data;
uint8_t actions_counter = 0;
@@ -933,6 +935,7 @@ fill_actions(struct rte_flow_action *actions, uint64_t *flow_actions,
.decap_data = decap_data,
.core_idx = core_idx,
.unique_data = unique_data,
+ .dst_port = dst_port,
};
if (hairpinq != 0) {
diff --git a/app/test-flow-perf/actions_gen.h b/app/test-flow-perf/actions_gen.h
index 8990686269..9e13b164f9 100644
--- a/app/test-flow-perf/actions_gen.h
+++ b/app/test-flow-perf/actions_gen.h
@@ -20,6 +20,6 @@
void fill_actions(struct rte_flow_action *actions, uint64_t *flow_actions,
uint32_t counter, uint16_t next_table, uint16_t hairpinq,
uint64_t encap_data, uint64_t decap_data, uint8_t core_idx,
- bool unique_data, uint8_t rx_queues_count);
+ bool unique_data, uint8_t rx_queues_count, uint16_t dst_port);
#endif /* FLOW_PERF_ACTION_GEN */
diff --git a/app/test-flow-perf/flow_gen.c b/app/test-flow-perf/flow_gen.c
index 51871dbfdc..c7b7652c02 100644
--- a/app/test-flow-perf/flow_gen.c
+++ b/app/test-flow-perf/flow_gen.c
@@ -45,6 +45,7 @@ generate_flow(uint16_t port_id,
uint16_t hairpinq,
uint64_t encap_data,
uint64_t decap_data,
+ uint16_t dst_port,
uint8_t core_idx,
uint8_t rx_queues_count,
bool unique_data,
@@ -64,7 +65,7 @@ generate_flow(uint16_t port_id,
fill_actions(actions, flow_actions,
outer_ip_src, next_table, hairpinq,
encap_data, decap_data, core_idx,
- unique_data, rx_queues_count);
+ unique_data, rx_queues_count, dst_port);
fill_items(items, flow_items, outer_ip_src, core_idx);
diff --git a/app/test-flow-perf/flow_gen.h b/app/test-flow-perf/flow_gen.h
index 1118a9fc14..46ce575ff8 100644
--- a/app/test-flow-perf/flow_gen.h
+++ b/app/test-flow-perf/flow_gen.h
@@ -34,6 +34,7 @@ generate_flow(uint16_t port_id,
uint16_t hairpinq,
uint64_t encap_data,
uint64_t decap_data,
+ uint16_t dst_port,
uint8_t core_idx,
uint8_t rx_queues_count,
bool unique_data,
diff --git a/app/test-flow-perf/main.c b/app/test-flow-perf/main.c
index 3ebc025fb2..c1ad9bb0a3 100644
--- a/app/test-flow-perf/main.c
+++ b/app/test-flow-perf/main.c
@@ -56,6 +56,7 @@ static uint64_t flow_attrs[MAX_ATTRS_NUM];
static uint8_t items_idx, actions_idx, attrs_idx;
static uint64_t ports_mask;
+static uint16_t dst_ports[RTE_MAX_ETHPORTS];
static volatile bool force_quit;
static bool dump_iterations;
static bool delete_flag;
@@ -619,7 +620,7 @@ args_parse(int argc, char **argv)
{ "icmpv4", 0, 0, 0 },
{ "icmpv6", 0, 0, 0 },
/* Actions */
- { "port-id", 0, 0, 0 },
+ { "port-id", 2, 0, 0 },
{ "rss", 0, 0, 0 },
{ "queue", 0, 0, 0 },
{ "jump", 0, 0, 0 },
@@ -657,6 +658,9 @@ args_parse(int argc, char **argv)
RTE_ETH_FOREACH_DEV(i)
ports_mask |= 1 << i;
+ for (i = 0; i < RTE_MAX_ETHPORTS; i++)
+ dst_ports[i] = PORT_ID_DST;
+
hairpin_queues_num = 0;
argvopt = argv;
@@ -811,6 +815,17 @@ args_parse(int argc, char **argv)
rte_exit(EXIT_FAILURE, "Invalid fwd port mask\n");
ports_mask = pm;
}
+ if (strcmp(lgopts[opt_idx].name,
+ "port-id") == 0) {
+ uint16_t port_idx = 0;
+ char *token;
+
+ token = strtok(optarg, ",");
+ while (token != NULL) {
+ dst_ports[port_idx++] = atoi(token);
+ token = strtok(NULL, ",");
+ }
+ }
if (strcmp(lgopts[opt_idx].name, "rxq") == 0) {
n = atoi(optarg);
rx_queues_count = (uint8_t) n;
@@ -1180,7 +1195,7 @@ destroy_flows(int port_id, uint8_t core_id, struct rte_flow **flows_list)
}
static struct rte_flow **
-insert_flows(int port_id, uint8_t core_id)
+insert_flows(int port_id, uint8_t core_id, uint16_t dst_port_id)
{
struct rte_flow **flows_list;
struct rte_flow_error error;
@@ -1226,8 +1241,8 @@ insert_flows(int port_id, uint8_t core_id)
*/
flow = generate_flow(port_id, 0, flow_attrs,
global_items, global_actions,
- flow_group, 0, 0, 0, 0, core_id, rx_queues_count,
- unique_data, &error);
+ flow_group, 0, 0, 0, 0, dst_port_id, core_id,
+ rx_queues_count, unique_data, &error);
if (flow == NULL) {
print_flow_error(error);
@@ -1241,8 +1256,8 @@ insert_flows(int port_id, uint8_t core_id)
flow = generate_flow(port_id, flow_group,
flow_attrs, flow_items, flow_actions,
JUMP_ACTION_TABLE, counter,
- hairpin_queues_num,
- encap_data, decap_data,
+ hairpin_queues_num, encap_data,
+ decap_data, dst_port_id,
core_id, rx_queues_count,
unique_data, &error);
@@ -1304,6 +1319,7 @@ static void
flows_handler(uint8_t core_id)
{
struct rte_flow **flows_list;
+ uint16_t port_idx = 0;
uint16_t nr_ports;
int port_id;
@@ -1323,7 +1339,8 @@ flows_handler(uint8_t core_id)
mc_pool.last_alloc[core_id] = (int64_t)dump_socket_mem(stdout);
if (has_meter())
meters_handler(port_id, core_id, METER_CREATE);
- flows_list = insert_flows(port_id, core_id);
+ flows_list = insert_flows(port_id, core_id,
+ dst_ports[port_idx++]);
if (flows_list == NULL)
rte_exit(EXIT_FAILURE, "Error: Insertion Failed!\n");
mc_pool.current_alloc[core_id] = (int64_t)dump_socket_mem(stdout);
diff --git a/doc/guides/tools/flow-perf.rst b/doc/guides/tools/flow-perf.rst
index 0855f88689..e608a44c24 100644
--- a/doc/guides/tools/flow-perf.rst
+++ b/doc/guides/tools/flow-perf.rst
@@ -231,6 +231,10 @@ Actions:
Port redirection destination is defined in user_parameters.h
under PORT_ID_DST, default value = 1.
+ It can also has optional parameter like --port-id=N[,M] to
+ specify the destination port, the number of values should be
+ the same with number of set bits in portmask.
+
* ``--rss``
Add RSS action to all flows actions,
The queues in RSS action will be all queues configured
--
2.33.0
^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [dpdk-dev] [V3] app/flow-perf: add destination ports parameter
2021-10-29 5:52 ` Sean Zhang
@ 2021-10-31 8:44 ` Wisam Monther
2021-11-05 9:50 ` Thomas Monjalon
0 siblings, 1 reply; 14+ messages in thread
From: Wisam Monther @ 2021-10-31 8:44 UTC (permalink / raw)
To: Sean Zhang (Networking SW), NBU-Contact-Thomas Monjalon
Cc: dev, Raslan Darawsheh
Hi,
> -----Original Message-----
> From: Sean Zhang (Networking SW) <xiazhang@nvidia.com>
> Sent: Friday, October 29, 2021 8:53 AM
> To: NBU-Contact-Thomas Monjalon <thomas@monjalon.net>; Wisam
> Monther <wisamm@nvidia.com>
> Cc: dev@dpdk.org; Raslan Darawsheh <rasland@nvidia.com>
> Subject: [V3] app/flow-perf: add destination ports parameter
>
> Add optional destination ports parameter for port-id action.
> The parameter is not must, and the value is 1 by default as before if the
> parameter not provided.
>
> For example:
>
> $ dpdk-test-flow-perf -w 08:00.0,representor=[0,1] -- --transfer \
> > --ingress --transfer --ether --portmask=0x2 --vxlan-encap \
> > --port-id=0
>
> This command means the rule created on representor 0 with port 0 as
> destination, since the portmask is 0x2 and dst-ports is 0:
>
> $ dpdk-test-flow-perf -w 08:00.0,representor=[0,1] \
> > -w 08:00.1,representor=[0,1]-- --transfer --ingress --transfer \
> > --ether --portmask=0x12 --vxlan-encap --port-id=0,3
>
> This command means the rules created on both representor 0 of PF 0 and PF
> 1, the destination port for the first represontor is PF 0, and the destination
> port for the other one it PF 1.
>
> Signed-off-by: Sean Zhang <xiazhang@nvidia.com>
> ---
> v3:
> resolve merging conflict
> v2:
> remove new added dst-ports parameter, reuse port-id with optional
> parameter
> ---
Reviewed-by: Wisam Jaddo <wisamm@nvidia.com>
BRs,
Wisam Jaddo
^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [dpdk-dev] [V3] app/flow-perf: add destination ports parameter
2021-10-31 8:44 ` Wisam Monther
@ 2021-11-05 9:50 ` Thomas Monjalon
0 siblings, 0 replies; 14+ messages in thread
From: Thomas Monjalon @ 2021-11-05 9:50 UTC (permalink / raw)
To: Sean Zhang (Networking SW), Raslan Darawsheh; +Cc: dev, Wisam Monther
> > Add optional destination ports parameter for port-id action.
> > The parameter is not must, and the value is 1 by default as before if the
> > parameter not provided.
> >
> > For example:
> >
> > $ dpdk-test-flow-perf -w 08:00.0,representor=[0,1] -- --transfer \
> > > --ingress --transfer --ether --portmask=0x2 --vxlan-encap \
> > > --port-id=0
> >
> > This command means the rule created on representor 0 with port 0 as
> > destination, since the portmask is 0x2 and dst-ports is 0:
> >
> > $ dpdk-test-flow-perf -w 08:00.0,representor=[0,1] \
> > > -w 08:00.1,representor=[0,1]-- --transfer --ingress --transfer \
> > > --ether --portmask=0x12 --vxlan-encap --port-id=0,3
> >
> > This command means the rules created on both representor 0 of PF 0 and PF
> > 1, the destination port for the first represontor is PF 0, and the destination
> > port for the other one it PF 1.
> >
> > Signed-off-by: Sean Zhang <xiazhang@nvidia.com>
> > ---
> > v3:
> > resolve merging conflict
> > v2:
> > remove new added dst-ports parameter, reuse port-id with optional
> > parameter
> > ---
>
> Reviewed-by: Wisam Jaddo <wisamm@nvidia.com>
Applied, thanks.
^ permalink raw reply [flat|nested] 14+ messages in thread