* [dpdk-dev] [PATCH 1/1] event/dlb2: fix vector based dequeue
@ 2021-05-12 18:24 McDaniel, Timothy
2021-05-18 15:01 ` Jerin Jacob
` (4 more replies)
0 siblings, 5 replies; 8+ messages in thread
From: McDaniel, Timothy @ 2021-05-12 18:24 UTC (permalink / raw)
Cc: dev, erik.g.carrillo, harry.van.haaren, jerinj, thomas, Timothy McDaniel
From: Timothy McDaniel <timothy.mcdaniel@intel.com>
This commit fixes the following bugs in the vector based
dequeue path:
- extract hw sched type
- update xstats
The default mode of operation was also changed from vector
optimized mode to scalar mode.
Fixes: 000a7b8e7582 ("event/dlb2: optimize dequeue operation")
Cc: timothy.mcdaniel@intel.com
Signed-off-by: Timothy McDaniel <timothy.mcdaniel@intel.com>
---
drivers/event/dlb2/dlb2.c | 40 ++++++++++++++++++++++++----------
drivers/event/dlb2/dlb2_priv.h | 7 +++---
2 files changed, 31 insertions(+), 16 deletions(-)
diff --git a/drivers/event/dlb2/dlb2.c b/drivers/event/dlb2/dlb2.c
index 3570678b9..b5745f6f4 100644
--- a/drivers/event/dlb2/dlb2.c
+++ b/drivers/event/dlb2/dlb2.c
@@ -376,11 +376,11 @@ set_default_depth_thresh(const char *key __rte_unused,
}
static int
-set_vector_opts_disab(const char *key __rte_unused,
+set_vector_opts_enab(const char *key __rte_unused,
const char *value,
void *opaque)
{
- bool *dlb2_vector_opts_disabled = opaque;
+ bool *dlb2_vector_opts_enabled = opaque;
if (value == NULL || opaque == NULL) {
DLB2_LOG_ERR("NULL pointer\n");
@@ -388,9 +388,9 @@ set_vector_opts_disab(const char *key __rte_unused,
}
if ((*value == 'y') || (*value == 'Y'))
- *dlb2_vector_opts_disabled = true;
+ *dlb2_vector_opts_enabled = true;
else
- *dlb2_vector_opts_disabled = false;
+ *dlb2_vector_opts_enabled = false;
return 0;
}
@@ -1469,7 +1469,7 @@ dlb2_hw_create_ldb_port(struct dlb2_eventdev *dlb2,
#else
if ((qm_port->cq_depth > 64) ||
(!rte_is_power_of_2(qm_port->cq_depth)) ||
- (dlb2->vector_opts_disabled == true))
+ (dlb2->vector_opts_enabled == false))
qm_port->use_scalar = true;
#endif
@@ -1665,7 +1665,7 @@ dlb2_hw_create_dir_port(struct dlb2_eventdev *dlb2,
#else
if ((qm_port->cq_depth > 64) ||
(!rte_is_power_of_2(qm_port->cq_depth)) ||
- (dlb2->vector_opts_disabled == true))
+ (dlb2->vector_opts_enabled == false))
qm_port->use_scalar = true;
#endif
@@ -3561,6 +3561,11 @@ _process_deq_qes_vec_impl(struct dlb2_port *qm_port,
int ev_qid2 = qm_port->qid_mappings[hw_qid2];
int ev_qid3 = qm_port->qid_mappings[hw_qid3];
+ int hw_sched0 = _mm_extract_epi8(v_qe_meta, 3) & 3ul;
+ int hw_sched1 = _mm_extract_epi8(v_qe_meta, 7) & 3ul;
+ int hw_sched2 = _mm_extract_epi8(v_qe_meta, 11) & 3ul;
+ int hw_sched3 = _mm_extract_epi8(v_qe_meta, 15) & 3ul;
+
v_qid_done = _mm_insert_epi8(v_qid_done, ev_qid0, 2);
v_qid_done = _mm_insert_epi8(v_qid_done, ev_qid1, 6);
v_qid_done = _mm_insert_epi8(v_qid_done, ev_qid2, 10);
@@ -3682,19 +3687,30 @@ _process_deq_qes_vec_impl(struct dlb2_port *qm_port,
v_ev_3 = _mm_blend_epi16(v_unpk_ev_23, v_qe_3, 0x0F);
v_ev_3 = _mm_alignr_epi8(v_ev_3, v_ev_3, 8);
_mm_storeu_si128((__m128i *)&events[3], v_ev_3);
+ DLB2_INC_STAT(qm_port->ev_port->stats.rx_sched_cnt[hw_sched3],
+ 1);
+
/* fallthrough */
case 3:
v_ev_2 = _mm_unpacklo_epi64(v_unpk_ev_23, v_qe_2);
_mm_storeu_si128((__m128i *)&events[2], v_ev_2);
+ DLB2_INC_STAT(qm_port->ev_port->stats.rx_sched_cnt[hw_sched2],
+ 1);
/* fallthrough */
case 2:
v_ev_1 = _mm_blend_epi16(v_unpk_ev_01, v_qe_1, 0x0F);
v_ev_1 = _mm_alignr_epi8(v_ev_1, v_ev_1, 8);
_mm_storeu_si128((__m128i *)&events[1], v_ev_1);
+ DLB2_INC_STAT(qm_port->ev_port->stats.rx_sched_cnt[hw_sched1],
+ 1);
+
/* fallthrough */
case 1:
v_ev_0 = _mm_unpacklo_epi64(v_unpk_ev_01, v_qe_0);
_mm_storeu_si128((__m128i *)&events[0], v_ev_0);
+ DLB2_INC_STAT(qm_port->ev_port->stats.rx_sched_cnt[hw_sched0],
+ 1);
+
}
}
@@ -4421,7 +4437,7 @@ dlb2_primary_eventdev_probe(struct rte_eventdev *dev,
dlb2->poll_interval = dlb2_args->poll_interval;
dlb2->sw_credit_quanta = dlb2_args->sw_credit_quanta;
dlb2->default_depth_thresh = dlb2_args->default_depth_thresh;
- dlb2->vector_opts_disabled = dlb2_args->vector_opts_disabled;
+ dlb2->vector_opts_enabled = dlb2_args->vector_opts_enabled;
err = dlb2_iface_open(&dlb2->qm_instance, name);
if (err < 0) {
@@ -4525,7 +4541,7 @@ dlb2_parse_params(const char *params,
DLB2_POLL_INTERVAL_ARG,
DLB2_SW_CREDIT_QUANTA_ARG,
DLB2_DEPTH_THRESH_ARG,
- DLB2_VECTOR_OPTS_DISAB_ARG,
+ DLB2_VECTOR_OPTS_ENAB_ARG,
NULL };
if (params != NULL && params[0] != '\0') {
@@ -4640,11 +4656,11 @@ dlb2_parse_params(const char *params,
}
ret = rte_kvargs_process(kvlist,
- DLB2_VECTOR_OPTS_DISAB_ARG,
- set_vector_opts_disab,
- &dlb2_args->vector_opts_disabled);
+ DLB2_VECTOR_OPTS_ENAB_ARG,
+ set_vector_opts_enab,
+ &dlb2_args->vector_opts_enabled);
if (ret != 0) {
- DLB2_LOG_ERR("%s: Error parsing vector opts disabled",
+ DLB2_LOG_ERR("%s: Error parsing vector opts enabled",
name);
rte_kvargs_free(kvlist);
return ret;
diff --git a/drivers/event/dlb2/dlb2_priv.h b/drivers/event/dlb2/dlb2_priv.h
index 3140764a5..e23702100 100644
--- a/drivers/event/dlb2/dlb2_priv.h
+++ b/drivers/event/dlb2/dlb2_priv.h
@@ -32,13 +32,12 @@
#define DLB2_MAX_NUM_EVENTS "max_num_events"
#define DLB2_NUM_DIR_CREDITS "num_dir_credits"
#define DEV_ID_ARG "dev_id"
-#define DLB2_DEFER_SCHED_ARG "defer_sched"
#define DLB2_QID_DEPTH_THRESH_ARG "qid_depth_thresh"
#define DLB2_COS_ARG "cos"
#define DLB2_POLL_INTERVAL_ARG "poll_interval"
#define DLB2_SW_CREDIT_QUANTA_ARG "sw_credit_quanta"
#define DLB2_DEPTH_THRESH_ARG "default_depth_thresh"
-#define DLB2_VECTOR_OPTS_DISAB_ARG "vector_opts_disable"
+#define DLB2_VECTOR_OPTS_ENAB_ARG "vector_opts_enable"
/* Begin HW related defines and structs */
@@ -566,7 +565,7 @@ struct dlb2_eventdev {
uint32_t new_event_limit;
int max_num_events_override;
int num_dir_credits_override;
- bool vector_opts_disabled;
+ bool vector_opts_enabled;
volatile enum dlb2_run_state run_state;
uint16_t num_dir_queues; /* total num of evdev dir queues requested */
union {
@@ -626,7 +625,7 @@ struct dlb2_devargs {
int poll_interval;
int sw_credit_quanta;
int default_depth_thresh;
- bool vector_opts_disabled;
+ bool vector_opts_enabled;
};
/* End Eventdev related defines and structs */
--
2.23.0
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [dpdk-dev] [PATCH 1/1] event/dlb2: fix vector based dequeue
2021-05-12 18:24 [dpdk-dev] [PATCH 1/1] event/dlb2: fix vector based dequeue McDaniel, Timothy
@ 2021-05-18 15:01 ` Jerin Jacob
2021-05-19 9:44 ` Thomas Monjalon
2021-05-20 16:11 ` [dpdk-dev] [PATCH] event/dlb2: fix extraction of HW scheduling type Timothy McDaniel
` (3 subsequent siblings)
4 siblings, 1 reply; 8+ messages in thread
From: Jerin Jacob @ 2021-05-18 15:01 UTC (permalink / raw)
To: McDaniel, Timothy, Thomas Monjalon
Cc: dpdk-dev, Erik Gabriel Carrillo, Van Haaren, Harry, Jerin Jacob
On Wed, May 12, 2021 at 11:55 PM McDaniel, Timothy
<timothy.mcdaniel@intel.com> wrote:
>
> From: Timothy McDaniel <timothy.mcdaniel@intel.com>
>
> This commit fixes the following bugs in the vector based
> dequeue path:
> - extract hw sched type
> - update xstats
>
> The default mode of operation was also changed from vector
> optimized mode to scalar mode.
>
> Fixes: 000a7b8e7582 ("event/dlb2: optimize dequeue operation")
> Cc: timothy.mcdaniel@intel.com
Removed this CC
>
> Signed-off-by: Timothy McDaniel <timothy.mcdaniel@intel.com>
@Thomas Monjalon Could you merge this patch as this is one only patch
for the final release from eventdev.
This patch is passing my sanity build tests.
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [dpdk-dev] [PATCH 1/1] event/dlb2: fix vector based dequeue
2021-05-18 15:01 ` Jerin Jacob
@ 2021-05-19 9:44 ` Thomas Monjalon
2021-05-19 15:23 ` McDaniel, Timothy
0 siblings, 1 reply; 8+ messages in thread
From: Thomas Monjalon @ 2021-05-19 9:44 UTC (permalink / raw)
To: McDaniel, Timothy
Cc: dev, Erik Gabriel Carrillo, Van Haaren, Harry, Jerin Jacob, Jerin Jacob
18/05/2021 17:01, Jerin Jacob:
> On Wed, May 12, 2021 at 11:55 PM McDaniel, Timothy
> <timothy.mcdaniel@intel.com> wrote:
> >
> > From: Timothy McDaniel <timothy.mcdaniel@intel.com>
> >
> > This commit fixes the following bugs in the vector based
> > dequeue path:
> > - extract hw sched type
> > - update xstats
> >
> > The default mode of operation was also changed from vector
> > optimized mode to scalar mode.
> >
> > Fixes: 000a7b8e7582 ("event/dlb2: optimize dequeue operation")
> > Cc: timothy.mcdaniel@intel.com
>
> Removed this CC
> >
> > Signed-off-by: Timothy McDaniel <timothy.mcdaniel@intel.com>
>
> @Thomas Monjalon Could you merge this patch as this is one only patch
> for the final release from eventdev.
> This patch is passing my sanity build tests.
This patch seems to change 3 unrelated things.
This is bad for tracking changes.
Please could you split?
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [dpdk-dev] [PATCH 1/1] event/dlb2: fix vector based dequeue
2021-05-19 9:44 ` Thomas Monjalon
@ 2021-05-19 15:23 ` McDaniel, Timothy
0 siblings, 0 replies; 8+ messages in thread
From: McDaniel, Timothy @ 2021-05-19 15:23 UTC (permalink / raw)
To: Thomas Monjalon, david.marchand
Cc: dev, Carrillo, Erik G, Van Haaren, Harry, Jerin Jacob, Jerin Jacob
> -----Original Message-----
> From: Thomas Monjalon <thomas@monjalon.net>
> Sent: Wednesday, May 19, 2021 4:44 AM
> To: McDaniel, Timothy <timothy.mcdaniel@intel.com>
> Cc: dev@dpdk.org; Carrillo, Erik G <erik.g.carrillo@intel.com>; Van Haaren,
> Harry <harry.van.haaren@intel.com>; Jerin Jacob <jerinj@marvell.com>; Jerin
> Jacob <jerinjacobk@gmail.com>
> Subject: Re: [dpdk-dev] [PATCH 1/1] event/dlb2: fix vector based dequeue
>
> 18/05/2021 17:01, Jerin Jacob:
> > On Wed, May 12, 2021 at 11:55 PM McDaniel, Timothy
> > <timothy.mcdaniel@intel.com> wrote:
> > >
> > > From: Timothy McDaniel <timothy.mcdaniel@intel.com>
> > >
> > > This commit fixes the following bugs in the vector based
> > > dequeue path:
> > > - extract hw sched type
> > > - update xstats
> > >
> > > The default mode of operation was also changed from vector
> > > optimized mode to scalar mode.
> > >
> > > Fixes: 000a7b8e7582 ("event/dlb2: optimize dequeue operation")
> > > Cc: timothy.mcdaniel@intel.com
> >
> > Removed this CC
> > >
> > > Signed-off-by: Timothy McDaniel <timothy.mcdaniel@intel.com>
> >
> > @Thomas Monjalon Could you merge this patch as this is one only patch
> > for the final release from eventdev.
> > This patch is passing my sanity build tests.
>
> This patch seems to change 3 unrelated things.
> This is bad for tracking changes.
> Please could you split?
>
I will split and resubmit both this patch and the documentation patch.
Thanks,
Tim
^ permalink raw reply [flat|nested] 8+ messages in thread
* [dpdk-dev] [PATCH] event/dlb2: fix extraction of HW scheduling type
2021-05-12 18:24 [dpdk-dev] [PATCH 1/1] event/dlb2: fix vector based dequeue McDaniel, Timothy
2021-05-18 15:01 ` Jerin Jacob
@ 2021-05-20 16:11 ` Timothy McDaniel
2021-05-20 16:12 ` [dpdk-dev] [PATCH] event/dlb2: make scalar mode dequeue the default Timothy McDaniel
` (2 subsequent siblings)
4 siblings, 0 replies; 8+ messages in thread
From: Timothy McDaniel @ 2021-05-20 16:11 UTC (permalink / raw)
Cc: dev, erik.g.carrillo, harry.van.haaren, jerinj, thomas,
david.marchand, timothy.mcdaniel
The HW scheduling type was not being extracted properly
in the vector optimizaed dequeue path. It was also not
being recorded in the xstats.
Fixes: 000a7b8e7582 ("event/dlb2: optimize dequeue operation")
Signed-off-by: Timothy McDaniel <timothy.mcdaniel@intel.com>
---
Cc: timothy.mcdaniel@intel.com
---
drivers/event/dlb2/dlb2.c | 13 +++++++++++++
1 file changed, 13 insertions(+)
diff --git a/drivers/event/dlb2/dlb2.c b/drivers/event/dlb2/dlb2.c
index 3570678b9..588c41ee7 100644
--- a/drivers/event/dlb2/dlb2.c
+++ b/drivers/event/dlb2/dlb2.c
@@ -3561,6 +3561,11 @@ _process_deq_qes_vec_impl(struct dlb2_port *qm_port,
int ev_qid2 = qm_port->qid_mappings[hw_qid2];
int ev_qid3 = qm_port->qid_mappings[hw_qid3];
+ int hw_sched0 = _mm_extract_epi8(v_qe_meta, 3) & 3ul;
+ int hw_sched1 = _mm_extract_epi8(v_qe_meta, 7) & 3ul;
+ int hw_sched2 = _mm_extract_epi8(v_qe_meta, 11) & 3ul;
+ int hw_sched3 = _mm_extract_epi8(v_qe_meta, 15) & 3ul;
+
v_qid_done = _mm_insert_epi8(v_qid_done, ev_qid0, 2);
v_qid_done = _mm_insert_epi8(v_qid_done, ev_qid1, 6);
v_qid_done = _mm_insert_epi8(v_qid_done, ev_qid2, 10);
@@ -3682,19 +3687,27 @@ _process_deq_qes_vec_impl(struct dlb2_port *qm_port,
v_ev_3 = _mm_blend_epi16(v_unpk_ev_23, v_qe_3, 0x0F);
v_ev_3 = _mm_alignr_epi8(v_ev_3, v_ev_3, 8);
_mm_storeu_si128((__m128i *)&events[3], v_ev_3);
+ DLB2_INC_STAT(qm_port->ev_port->stats.rx_sched_cnt[hw_sched3],
+ 1);
/* fallthrough */
case 3:
v_ev_2 = _mm_unpacklo_epi64(v_unpk_ev_23, v_qe_2);
_mm_storeu_si128((__m128i *)&events[2], v_ev_2);
+ DLB2_INC_STAT(qm_port->ev_port->stats.rx_sched_cnt[hw_sched2],
+ 1);
/* fallthrough */
case 2:
v_ev_1 = _mm_blend_epi16(v_unpk_ev_01, v_qe_1, 0x0F);
v_ev_1 = _mm_alignr_epi8(v_ev_1, v_ev_1, 8);
_mm_storeu_si128((__m128i *)&events[1], v_ev_1);
+ DLB2_INC_STAT(qm_port->ev_port->stats.rx_sched_cnt[hw_sched1],
+ 1);
/* fallthrough */
case 1:
v_ev_0 = _mm_unpacklo_epi64(v_unpk_ev_01, v_qe_0);
_mm_storeu_si128((__m128i *)&events[0], v_ev_0);
+ DLB2_INC_STAT(qm_port->ev_port->stats.rx_sched_cnt[hw_sched0],
+ 1);
}
}
--
2.23.0
^ permalink raw reply [flat|nested] 8+ messages in thread
* [dpdk-dev] [PATCH] event/dlb2: make scalar mode dequeue the default
2021-05-12 18:24 [dpdk-dev] [PATCH 1/1] event/dlb2: fix vector based dequeue McDaniel, Timothy
2021-05-18 15:01 ` Jerin Jacob
2021-05-20 16:11 ` [dpdk-dev] [PATCH] event/dlb2: fix extraction of HW scheduling type Timothy McDaniel
@ 2021-05-20 16:12 ` Timothy McDaniel
2021-05-20 16:13 ` [dpdk-dev] [PATCH] event/dlb2: remove references to deferred scheduling Timothy McDaniel
2021-05-20 18:08 ` [dpdk-dev] [PATCH v2] event/dlb2: make scalar mode dequeue the default Timothy McDaniel
4 siblings, 0 replies; 8+ messages in thread
From: Timothy McDaniel @ 2021-05-20 16:12 UTC (permalink / raw)
Cc: dev, erik.g.carrillo, harry.van.haaren, jerinj, thomas,
david.marchand, timothy.mcdaniel
Optimized dequeue using x86 vector instructions was added
in 21.05, but due to limited testing the default has been
changed back to the scalar mode implementation. The vector mode
implementation can be enabled via the devargs option
"vector_opts_enabled=<y/Y>".
Fixes: 000a7b8e7582 ("event/dlb2: optimize dequeue operation")
Signed-off-by: Timothy McDaniel <timothy.mcdaniel@intel.com>
---
Cc: timothy.mcdaniel@intel.com
---
doc/guides/eventdevs/dlb2.rst | 13 +++++++++++++
drivers/event/dlb2/dlb2.c | 24 ++++++++++++------------
drivers/event/dlb2/dlb2_priv.h | 6 +++---
3 files changed, 28 insertions(+), 15 deletions(-)
diff --git a/doc/guides/eventdevs/dlb2.rst b/doc/guides/eventdevs/dlb2.rst
index c60c454d6..3f4bab97a 100644
--- a/doc/guides/eventdevs/dlb2.rst
+++ b/doc/guides/eventdevs/dlb2.rst
@@ -367,3 +367,16 @@ Class of service can be specified in the devargs, as follows
.. code-block:: console
--vdev=dlb2_event,cos=<0..4>
+
+Use X86 Vector Instructions
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+DLB supports using x86 vector instructions to optimize the data path.
+
+The default mode of operation is to use scalar instructions, but
+the use of vector instructions can be enabled in the devargs, as
+follows
+
+ .. code-block:: console
+
+ --allow ea:00.0,vector_opts_enabled=<y/Y>
diff --git a/drivers/event/dlb2/dlb2.c b/drivers/event/dlb2/dlb2.c
index 588c41ee7..0022f65fc 100644
--- a/drivers/event/dlb2/dlb2.c
+++ b/drivers/event/dlb2/dlb2.c
@@ -376,11 +376,11 @@ set_default_depth_thresh(const char *key __rte_unused,
}
static int
-set_vector_opts_disab(const char *key __rte_unused,
+set_vector_opts_enab(const char *key __rte_unused,
const char *value,
void *opaque)
{
- bool *dlb2_vector_opts_disabled = opaque;
+ bool *dlb2_vector_opts_enabled = opaque;
if (value == NULL || opaque == NULL) {
DLB2_LOG_ERR("NULL pointer\n");
@@ -388,9 +388,9 @@ set_vector_opts_disab(const char *key __rte_unused,
}
if ((*value == 'y') || (*value == 'Y'))
- *dlb2_vector_opts_disabled = true;
+ *dlb2_vector_opts_enabled = true;
else
- *dlb2_vector_opts_disabled = false;
+ *dlb2_vector_opts_enabled = false;
return 0;
}
@@ -1469,7 +1469,7 @@ dlb2_hw_create_ldb_port(struct dlb2_eventdev *dlb2,
#else
if ((qm_port->cq_depth > 64) ||
(!rte_is_power_of_2(qm_port->cq_depth)) ||
- (dlb2->vector_opts_disabled == true))
+ (dlb2->vector_opts_enabled == false))
qm_port->use_scalar = true;
#endif
@@ -1665,7 +1665,7 @@ dlb2_hw_create_dir_port(struct dlb2_eventdev *dlb2,
#else
if ((qm_port->cq_depth > 64) ||
(!rte_is_power_of_2(qm_port->cq_depth)) ||
- (dlb2->vector_opts_disabled == true))
+ (dlb2->vector_opts_enabled == false))
qm_port->use_scalar = true;
#endif
@@ -4434,7 +4434,7 @@ dlb2_primary_eventdev_probe(struct rte_eventdev *dev,
dlb2->poll_interval = dlb2_args->poll_interval;
dlb2->sw_credit_quanta = dlb2_args->sw_credit_quanta;
dlb2->default_depth_thresh = dlb2_args->default_depth_thresh;
- dlb2->vector_opts_disabled = dlb2_args->vector_opts_disabled;
+ dlb2->vector_opts_enabled = dlb2_args->vector_opts_enabled;
err = dlb2_iface_open(&dlb2->qm_instance, name);
if (err < 0) {
@@ -4538,7 +4538,7 @@ dlb2_parse_params(const char *params,
DLB2_POLL_INTERVAL_ARG,
DLB2_SW_CREDIT_QUANTA_ARG,
DLB2_DEPTH_THRESH_ARG,
- DLB2_VECTOR_OPTS_DISAB_ARG,
+ DLB2_VECTOR_OPTS_ENAB_ARG,
NULL };
if (params != NULL && params[0] != '\0') {
@@ -4653,11 +4653,11 @@ dlb2_parse_params(const char *params,
}
ret = rte_kvargs_process(kvlist,
- DLB2_VECTOR_OPTS_DISAB_ARG,
- set_vector_opts_disab,
- &dlb2_args->vector_opts_disabled);
+ DLB2_VECTOR_OPTS_ENAB_ARG,
+ set_vector_opts_enab,
+ &dlb2_args->vector_opts_enabled);
if (ret != 0) {
- DLB2_LOG_ERR("%s: Error parsing vector opts disabled",
+ DLB2_LOG_ERR("%s: Error parsing vector opts enabled",
name);
rte_kvargs_free(kvlist);
return ret;
diff --git a/drivers/event/dlb2/dlb2_priv.h b/drivers/event/dlb2/dlb2_priv.h
index b1225af37..bb87072da 100644
--- a/drivers/event/dlb2/dlb2_priv.h
+++ b/drivers/event/dlb2/dlb2_priv.h
@@ -37,7 +37,7 @@
#define DLB2_POLL_INTERVAL_ARG "poll_interval"
#define DLB2_SW_CREDIT_QUANTA_ARG "sw_credit_quanta"
#define DLB2_DEPTH_THRESH_ARG "default_depth_thresh"
-#define DLB2_VECTOR_OPTS_DISAB_ARG "vector_opts_disable"
+#define DLB2_VECTOR_OPTS_ENAB_ARG "vector_opts_enable"
/* Begin HW related defines and structs */
@@ -565,7 +565,7 @@ struct dlb2_eventdev {
uint32_t new_event_limit;
int max_num_events_override;
int num_dir_credits_override;
- bool vector_opts_disabled;
+ bool vector_opts_enabled;
volatile enum dlb2_run_state run_state;
uint16_t num_dir_queues; /* total num of evdev dir queues requested */
union {
@@ -623,7 +623,7 @@ struct dlb2_devargs {
int poll_interval;
int sw_credit_quanta;
int default_depth_thresh;
- bool vector_opts_disabled;
+ bool vector_opts_enabled;
};
/* End Eventdev related defines and structs */
--
2.23.0
^ permalink raw reply [flat|nested] 8+ messages in thread
* [dpdk-dev] [PATCH] event/dlb2: remove references to deferred scheduling
2021-05-12 18:24 [dpdk-dev] [PATCH 1/1] event/dlb2: fix vector based dequeue McDaniel, Timothy
` (2 preceding siblings ...)
2021-05-20 16:12 ` [dpdk-dev] [PATCH] event/dlb2: make scalar mode dequeue the default Timothy McDaniel
@ 2021-05-20 16:13 ` Timothy McDaniel
2021-05-20 18:08 ` [dpdk-dev] [PATCH v2] event/dlb2: make scalar mode dequeue the default Timothy McDaniel
4 siblings, 0 replies; 8+ messages in thread
From: Timothy McDaniel @ 2021-05-20 16:13 UTC (permalink / raw)
Cc: dev, erik.g.carrillo, harry.van.haaren, jerinj, thomas,
david.marchand, stable, timothy.mcdaniel
Deferred scheduling is a DLB v1.0 feature, and is not valid for
DLB v2.0 or v2.5.
Fixes: a3c8a44634e3 ("event/dlb2: remove useless code")
Cc: stable@dpdk.org
Signed-off-by: Timothy McDaniel <timothy.mcdaniel@intel.com>
---
Cc: timothy.mcdaniel@intel.com
---
doc/guides/eventdevs/dlb2.rst | 21 ---------------------
drivers/event/dlb2/dlb2_priv.h | 3 ---
2 files changed, 24 deletions(-)
diff --git a/doc/guides/eventdevs/dlb2.rst b/doc/guides/eventdevs/dlb2.rst
index 31de6bc47..c60c454d6 100644
--- a/doc/guides/eventdevs/dlb2.rst
+++ b/doc/guides/eventdevs/dlb2.rst
@@ -293,27 +293,6 @@ The PMD does not support the following configuration sequences:
This sequence is not supported because the event device must be reconfigured
before its ports or queues can be.
-Deferred Scheduling
-~~~~~~~~~~~~~~~~~~~
-
-The DLB PMD's default behavior for managing a CQ is to "pop" the CQ once per
-dequeued event before returning from rte_event_dequeue_burst(). This frees the
-corresponding entries in the CQ, which enables the DLB to schedule more events
-to it.
-
-To support applications seeking finer-grained scheduling control -- for example
-deferring scheduling to get the best possible priority scheduling and
-load-balancing -- the PMD supports a deferred scheduling mode. In this mode,
-the CQ entry is not popped until the *subsequent* rte_event_dequeue_burst()
-call. This mode only applies to load-balanced event ports with dequeue depth of
-1.
-
-To enable deferred scheduling, use the defer_sched vdev argument like so:
-
- .. code-block:: console
-
- --vdev=dlb2_event,defer_sched=on
-
Atomic Inflights Allocation
~~~~~~~~~~~~~~~~~~~~~~~~~~~
diff --git a/drivers/event/dlb2/dlb2_priv.h b/drivers/event/dlb2/dlb2_priv.h
index 3140764a5..b1225af37 100644
--- a/drivers/event/dlb2/dlb2_priv.h
+++ b/drivers/event/dlb2/dlb2_priv.h
@@ -32,7 +32,6 @@
#define DLB2_MAX_NUM_EVENTS "max_num_events"
#define DLB2_NUM_DIR_CREDITS "num_dir_credits"
#define DEV_ID_ARG "dev_id"
-#define DLB2_DEFER_SCHED_ARG "defer_sched"
#define DLB2_QID_DEPTH_THRESH_ARG "qid_depth_thresh"
#define DLB2_COS_ARG "cos"
#define DLB2_POLL_INTERVAL_ARG "poll_interval"
@@ -585,7 +584,6 @@ struct dlb2_eventdev {
uint16_t num_dir_ports; /* total num of dir ports requested */
bool umwait_allowed;
bool global_dequeue_wait; /* Not using per dequeue wait if true */
- bool defer_sched;
enum dlb2_cq_poll_modes poll_mode;
int poll_interval;
int sw_credit_quanta;
@@ -620,7 +618,6 @@ struct dlb2_devargs {
int max_num_events;
int num_dir_credits_override;
int dev_id;
- int defer_sched;
struct dlb2_qid_depth_thresholds qid_depth_thresholds;
enum dlb2_cos cos_id;
int poll_interval;
--
2.23.0
^ permalink raw reply [flat|nested] 8+ messages in thread
* [dpdk-dev] [PATCH v2] event/dlb2: make scalar mode dequeue the default
2021-05-12 18:24 [dpdk-dev] [PATCH 1/1] event/dlb2: fix vector based dequeue McDaniel, Timothy
` (3 preceding siblings ...)
2021-05-20 16:13 ` [dpdk-dev] [PATCH] event/dlb2: remove references to deferred scheduling Timothy McDaniel
@ 2021-05-20 18:08 ` Timothy McDaniel
4 siblings, 0 replies; 8+ messages in thread
From: Timothy McDaniel @ 2021-05-20 18:08 UTC (permalink / raw)
Cc: dev, erik.g.carrillo, harry.van.haaren, jerinj, thomas,
david.marchand, timothy.mcdaniel
Optimized dequeue using x86 vector instructions was added
in 21.05, but due to limited testing the default has been
changed back to the scalar mode implementation. The vector mode
implementation can be enabled via the devargs option
"vector_opts_enabled=<y/Y>".
Fixes: 000a7b8e7582 ("event/dlb2: optimize dequeue operation")
Signed-off-by: Timothy McDaniel <timothy.mcdaniel@intel.com>
---
Cc: timothy.mcdaniel@intel.com
---
doc/guides/eventdevs/dlb2.rst | 13 +++++++++++++
drivers/event/dlb2/dlb2.c | 24 ++++++++++++------------
drivers/event/dlb2/dlb2_priv.h | 6 +++---
3 files changed, 28 insertions(+), 15 deletions(-)
diff --git a/doc/guides/eventdevs/dlb2.rst b/doc/guides/eventdevs/dlb2.rst
index c60c454d6..acdb00587 100644
--- a/doc/guides/eventdevs/dlb2.rst
+++ b/doc/guides/eventdevs/dlb2.rst
@@ -367,3 +367,16 @@ Class of service can be specified in the devargs, as follows
.. code-block:: console
--vdev=dlb2_event,cos=<0..4>
+
+Use X86 Vector Instructions
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+DLB supports using x86 vector instructions to optimize the data path.
+
+The default mode of operation is to use scalar instructions, but
+the use of vector instructions can be enabled in the devargs, as
+follows
+
+ .. code-block:: console
+
+ --allow ea:00.0,vector_opts_enabled=<y/Y>
diff --git a/drivers/event/dlb2/dlb2.c b/drivers/event/dlb2/dlb2.c
index 588c41ee7..0022f65fc 100644
--- a/drivers/event/dlb2/dlb2.c
+++ b/drivers/event/dlb2/dlb2.c
@@ -376,11 +376,11 @@ set_default_depth_thresh(const char *key __rte_unused,
}
static int
-set_vector_opts_disab(const char *key __rte_unused,
+set_vector_opts_enab(const char *key __rte_unused,
const char *value,
void *opaque)
{
- bool *dlb2_vector_opts_disabled = opaque;
+ bool *dlb2_vector_opts_enabled = opaque;
if (value == NULL || opaque == NULL) {
DLB2_LOG_ERR("NULL pointer\n");
@@ -388,9 +388,9 @@ set_vector_opts_disab(const char *key __rte_unused,
}
if ((*value == 'y') || (*value == 'Y'))
- *dlb2_vector_opts_disabled = true;
+ *dlb2_vector_opts_enabled = true;
else
- *dlb2_vector_opts_disabled = false;
+ *dlb2_vector_opts_enabled = false;
return 0;
}
@@ -1469,7 +1469,7 @@ dlb2_hw_create_ldb_port(struct dlb2_eventdev *dlb2,
#else
if ((qm_port->cq_depth > 64) ||
(!rte_is_power_of_2(qm_port->cq_depth)) ||
- (dlb2->vector_opts_disabled == true))
+ (dlb2->vector_opts_enabled == false))
qm_port->use_scalar = true;
#endif
@@ -1665,7 +1665,7 @@ dlb2_hw_create_dir_port(struct dlb2_eventdev *dlb2,
#else
if ((qm_port->cq_depth > 64) ||
(!rte_is_power_of_2(qm_port->cq_depth)) ||
- (dlb2->vector_opts_disabled == true))
+ (dlb2->vector_opts_enabled == false))
qm_port->use_scalar = true;
#endif
@@ -4434,7 +4434,7 @@ dlb2_primary_eventdev_probe(struct rte_eventdev *dev,
dlb2->poll_interval = dlb2_args->poll_interval;
dlb2->sw_credit_quanta = dlb2_args->sw_credit_quanta;
dlb2->default_depth_thresh = dlb2_args->default_depth_thresh;
- dlb2->vector_opts_disabled = dlb2_args->vector_opts_disabled;
+ dlb2->vector_opts_enabled = dlb2_args->vector_opts_enabled;
err = dlb2_iface_open(&dlb2->qm_instance, name);
if (err < 0) {
@@ -4538,7 +4538,7 @@ dlb2_parse_params(const char *params,
DLB2_POLL_INTERVAL_ARG,
DLB2_SW_CREDIT_QUANTA_ARG,
DLB2_DEPTH_THRESH_ARG,
- DLB2_VECTOR_OPTS_DISAB_ARG,
+ DLB2_VECTOR_OPTS_ENAB_ARG,
NULL };
if (params != NULL && params[0] != '\0') {
@@ -4653,11 +4653,11 @@ dlb2_parse_params(const char *params,
}
ret = rte_kvargs_process(kvlist,
- DLB2_VECTOR_OPTS_DISAB_ARG,
- set_vector_opts_disab,
- &dlb2_args->vector_opts_disabled);
+ DLB2_VECTOR_OPTS_ENAB_ARG,
+ set_vector_opts_enab,
+ &dlb2_args->vector_opts_enabled);
if (ret != 0) {
- DLB2_LOG_ERR("%s: Error parsing vector opts disabled",
+ DLB2_LOG_ERR("%s: Error parsing vector opts enabled",
name);
rte_kvargs_free(kvlist);
return ret;
diff --git a/drivers/event/dlb2/dlb2_priv.h b/drivers/event/dlb2/dlb2_priv.h
index b1225af37..bb87072da 100644
--- a/drivers/event/dlb2/dlb2_priv.h
+++ b/drivers/event/dlb2/dlb2_priv.h
@@ -37,7 +37,7 @@
#define DLB2_POLL_INTERVAL_ARG "poll_interval"
#define DLB2_SW_CREDIT_QUANTA_ARG "sw_credit_quanta"
#define DLB2_DEPTH_THRESH_ARG "default_depth_thresh"
-#define DLB2_VECTOR_OPTS_DISAB_ARG "vector_opts_disable"
+#define DLB2_VECTOR_OPTS_ENAB_ARG "vector_opts_enable"
/* Begin HW related defines and structs */
@@ -565,7 +565,7 @@ struct dlb2_eventdev {
uint32_t new_event_limit;
int max_num_events_override;
int num_dir_credits_override;
- bool vector_opts_disabled;
+ bool vector_opts_enabled;
volatile enum dlb2_run_state run_state;
uint16_t num_dir_queues; /* total num of evdev dir queues requested */
union {
@@ -623,7 +623,7 @@ struct dlb2_devargs {
int poll_interval;
int sw_credit_quanta;
int default_depth_thresh;
- bool vector_opts_disabled;
+ bool vector_opts_enabled;
};
/* End Eventdev related defines and structs */
--
2.23.0
^ permalink raw reply [flat|nested] 8+ messages in thread
end of thread, other threads:[~2021-05-20 18:09 UTC | newest]
Thread overview: 8+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-05-12 18:24 [dpdk-dev] [PATCH 1/1] event/dlb2: fix vector based dequeue McDaniel, Timothy
2021-05-18 15:01 ` Jerin Jacob
2021-05-19 9:44 ` Thomas Monjalon
2021-05-19 15:23 ` McDaniel, Timothy
2021-05-20 16:11 ` [dpdk-dev] [PATCH] event/dlb2: fix extraction of HW scheduling type Timothy McDaniel
2021-05-20 16:12 ` [dpdk-dev] [PATCH] event/dlb2: make scalar mode dequeue the default Timothy McDaniel
2021-05-20 16:13 ` [dpdk-dev] [PATCH] event/dlb2: remove references to deferred scheduling Timothy McDaniel
2021-05-20 18:08 ` [dpdk-dev] [PATCH v2] event/dlb2: make scalar mode dequeue the default Timothy McDaniel
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).