From: Marcin Danilewicz <marcinx.danilewicz@intel.com>
To: dev@dpdk.org
Subject: [PATCH v3] sched: enable/disable TC OV at runtime
Date: Wed, 27 Apr 2022 08:58:48 +0000 [thread overview]
Message-ID: <20220427085848.491395-1-marcinx.danilewicz@intel.com> (raw)
Added new API to enable or disable TC over subscription for best
effort traffic class at subport level.
Added changes after review and increased throughput.
By default TC OV is disabled.
Signed-off-by: Marcin Danilewicz <marcinx.danilewicz@intel.com>
---
lib/sched/rte_sched.c | 189 +++++++++++++++++++++++++++++++++++-------
lib/sched/rte_sched.h | 18 ++++
lib/sched/version.map | 3 +
3 files changed, 178 insertions(+), 32 deletions(-)
diff --git a/lib/sched/rte_sched.c b/lib/sched/rte_sched.c
index ec74bee939..6e7d81df46 100644
--- a/lib/sched/rte_sched.c
+++ b/lib/sched/rte_sched.c
@@ -213,6 +213,9 @@ struct rte_sched_subport {
uint8_t *bmp_array;
struct rte_mbuf **queue_array;
uint8_t memory[0] __rte_cache_aligned;
+
+ /* TC oversubscription activation */
+ int is_tc_ov_enabled;
} __rte_cache_aligned;
struct rte_sched_port {
@@ -1165,6 +1168,45 @@ rte_sched_cman_config(struct rte_sched_port *port,
}
#endif
+int
+rte_sched_subport_tc_ov_config(struct rte_sched_port *port,
+ uint32_t subport_id,
+ bool tc_ov_enable)
+{
+ struct rte_sched_subport *s;
+ struct rte_sched_subport_profile *profile;
+
+ if (port == NULL) {
+ RTE_LOG(ERR, SCHED,
+ "%s: Incorrect value for parameter port\n", __func__);
+ return -EINVAL;
+ }
+
+ if (subport_id >= port->n_subports_per_port) {
+ RTE_LOG(ERR, SCHED,
+ "%s: Incorrect value for parameter subport id\n", __func__);
+ return -EINVAL;
+ }
+
+ s = port->subports[subport_id];
+ s->is_tc_ov_enabled = tc_ov_enable ? 1 : 0;
+
+ if (s->is_tc_ov_enabled) {
+ /* TC oversubscription */
+ s->tc_ov_wm_min = port->mtu;
+ s->tc_ov_period_id = 0;
+ s->tc_ov = 0;
+ s->tc_ov_n = 0;
+ s->tc_ov_rate = 0;
+
+ profile = port->subport_profiles + s->profile;
+ s->tc_ov_wm_max = rte_sched_time_ms_to_bytes(profile->tc_period,
+ s->pipe_tc_be_rate_max);
+ s->tc_ov_wm = s->tc_ov_wm_max;
+ }
+ return 0;
+}
+
int
rte_sched_subport_config(struct rte_sched_port *port,
uint32_t subport_id,
@@ -1254,6 +1296,9 @@ rte_sched_subport_config(struct rte_sched_port *port,
s->n_pipe_profiles = params->n_pipe_profiles;
s->n_max_pipe_profiles = params->n_max_pipe_profiles;
+ /* TC over-subscription is disabled by default */
+ s->is_tc_ov_enabled = 0;
+
#ifdef RTE_SCHED_CMAN
if (params->cman_params != NULL) {
s->cman_enabled = true;
@@ -1316,13 +1361,6 @@ rte_sched_subport_config(struct rte_sched_port *port,
for (i = 0; i < RTE_SCHED_PORT_N_GRINDERS; i++)
s->grinder_base_bmp_pos[i] = RTE_SCHED_PIPE_INVALID;
-
- /* TC oversubscription */
- s->tc_ov_wm_min = port->mtu;
- s->tc_ov_period_id = 0;
- s->tc_ov = 0;
- s->tc_ov_n = 0;
- s->tc_ov_rate = 0;
}
{
@@ -1342,9 +1380,6 @@ rte_sched_subport_config(struct rte_sched_port *port,
else
profile->tc_credits_per_period[i] = 0;
- s->tc_ov_wm_max = rte_sched_time_ms_to_bytes(profile->tc_period,
- s->pipe_tc_be_rate_max);
- s->tc_ov_wm = s->tc_ov_wm_max;
s->profile = subport_profile_id;
}
@@ -1417,17 +1452,20 @@ rte_sched_pipe_config(struct rte_sched_port *port,
double pipe_tc_be_rate =
(double) params->tc_credits_per_period[RTE_SCHED_TRAFFIC_CLASS_BE]
/ (double) params->tc_period;
- uint32_t tc_be_ov = s->tc_ov;
- /* Unplug pipe from its subport */
- s->tc_ov_n -= params->tc_ov_weight;
- s->tc_ov_rate -= pipe_tc_be_rate;
- s->tc_ov = s->tc_ov_rate > subport_tc_be_rate;
+ if (s->is_tc_ov_enabled) {
+ uint32_t tc_be_ov = s->tc_ov;
- if (s->tc_ov != tc_be_ov) {
- RTE_LOG(DEBUG, SCHED,
- "Subport %u Best-effort TC oversubscription is OFF (%.4lf >= %.4lf)\n",
- subport_id, subport_tc_be_rate, s->tc_ov_rate);
+ /* Unplug pipe from its subport */
+ s->tc_ov_n -= params->tc_ov_weight;
+ s->tc_ov_rate -= pipe_tc_be_rate;
+ s->tc_ov = s->tc_ov_rate > subport_tc_be_rate;
+
+ if (s->tc_ov != tc_be_ov) {
+ RTE_LOG(DEBUG, SCHED,
+ "Subport %u Best-effort TC oversubscription is OFF (%.4lf >= %.4lf)\n",
+ subport_id, subport_tc_be_rate, s->tc_ov_rate);
+ }
}
/* Reset the pipe */
@@ -1460,19 +1498,22 @@ rte_sched_pipe_config(struct rte_sched_port *port,
double pipe_tc_be_rate =
(double) params->tc_credits_per_period[RTE_SCHED_TRAFFIC_CLASS_BE]
/ (double) params->tc_period;
- uint32_t tc_be_ov = s->tc_ov;
- s->tc_ov_n += params->tc_ov_weight;
- s->tc_ov_rate += pipe_tc_be_rate;
- s->tc_ov = s->tc_ov_rate > subport_tc_be_rate;
+ if (s->is_tc_ov_enabled) {
+ uint32_t tc_be_ov = s->tc_ov;
+
+ s->tc_ov_n += params->tc_ov_weight;
+ s->tc_ov_rate += pipe_tc_be_rate;
+ s->tc_ov = s->tc_ov_rate > subport_tc_be_rate;
- if (s->tc_ov != tc_be_ov) {
- RTE_LOG(DEBUG, SCHED,
- "Subport %u Best effort TC oversubscription is ON (%.4lf < %.4lf)\n",
- subport_id, subport_tc_be_rate, s->tc_ov_rate);
+ if (s->tc_ov != tc_be_ov) {
+ RTE_LOG(DEBUG, SCHED,
+ "Subport %u Best effort TC oversubscription is ON (%.4lf < %.4lf)\n",
+ subport_id, subport_tc_be_rate, s->tc_ov_rate);
+ }
+ p->tc_ov_period_id = s->tc_ov_period_id;
+ p->tc_ov_credits = s->tc_ov_wm;
}
- p->tc_ov_period_id = s->tc_ov_period_id;
- p->tc_ov_credits = s->tc_ov_wm;
}
return 0;
@@ -2318,6 +2359,45 @@ grinder_credits_update(struct rte_sched_port *port,
pipe->tb_credits = RTE_MIN(pipe->tb_credits, params->tb_size);
pipe->tb_time += n_periods * params->tb_period;
+ /* Subport TCs */
+ if (unlikely(port->time >= subport->tc_time)) {
+ for (i = 0; i < RTE_SCHED_TRAFFIC_CLASSES_PER_PIPE; i++)
+ subport->tc_credits[i] = sp->tc_credits_per_period[i];
+
+ subport->tc_time = port->time + sp->tc_period;
+ }
+
+ /* Pipe TCs */
+ if (unlikely(port->time >= pipe->tc_time)) {
+ for (i = 0; i < RTE_SCHED_TRAFFIC_CLASSES_PER_PIPE; i++)
+ pipe->tc_credits[i] = params->tc_credits_per_period[i];
+ pipe->tc_time = port->time + params->tc_period;
+ }
+}
+
+static inline void
+grinder_credits_update_with_tc_ov(struct rte_sched_port *port,
+ struct rte_sched_subport *subport, uint32_t pos)
+{
+ struct rte_sched_grinder *grinder = subport->grinder + pos;
+ struct rte_sched_pipe *pipe = grinder->pipe;
+ struct rte_sched_pipe_profile *params = grinder->pipe_params;
+ struct rte_sched_subport_profile *sp = grinder->subport_params;
+ uint64_t n_periods;
+ uint32_t i;
+
+ /* Subport TB */
+ n_periods = (port->time - subport->tb_time) / sp->tb_period;
+ subport->tb_credits += n_periods * sp->tb_credits_per_period;
+ subport->tb_credits = RTE_MIN(subport->tb_credits, sp->tb_size);
+ subport->tb_time += n_periods * sp->tb_period;
+
+ /* Pipe TB */
+ n_periods = (port->time - pipe->tb_time) / params->tb_period;
+ pipe->tb_credits += n_periods * params->tb_credits_per_period;
+ pipe->tb_credits = RTE_MIN(pipe->tb_credits, params->tb_size);
+ pipe->tb_time += n_periods * params->tb_period;
+
/* Subport TCs */
if (unlikely(port->time >= subport->tc_time)) {
subport->tc_ov_wm =
@@ -2348,6 +2428,39 @@ grinder_credits_update(struct rte_sched_port *port,
static inline int
grinder_credits_check(struct rte_sched_port *port,
struct rte_sched_subport *subport, uint32_t pos)
+{
+ struct rte_sched_grinder *grinder = subport->grinder + pos;
+ struct rte_sched_pipe *pipe = grinder->pipe;
+ struct rte_mbuf *pkt = grinder->pkt;
+ uint32_t tc_index = grinder->tc_index;
+ uint64_t pkt_len = pkt->pkt_len + port->frame_overhead;
+ uint64_t subport_tb_credits = subport->tb_credits;
+ uint64_t subport_tc_credits = subport->tc_credits[tc_index];
+ uint64_t pipe_tb_credits = pipe->tb_credits;
+ uint64_t pipe_tc_credits = pipe->tc_credits[tc_index];
+ int enough_credits;
+
+ /* Check pipe and subport credits */
+ enough_credits = (pkt_len <= subport_tb_credits) &&
+ (pkt_len <= subport_tc_credits) &&
+ (pkt_len <= pipe_tb_credits) &&
+ (pkt_len <= pipe_tc_credits);
+
+ if (!enough_credits)
+ return 0;
+
+ /* Update pipe and subport credits */
+ subport->tb_credits -= pkt_len;
+ subport->tc_credits[tc_index] -= pkt_len;
+ pipe->tb_credits -= pkt_len;
+ pipe->tc_credits[tc_index] -= pkt_len;
+
+ return 1;
+}
+
+static inline int
+grinder_credits_check_with_tc_ov(struct rte_sched_port *port,
+ struct rte_sched_subport *subport, uint32_t pos)
{
struct rte_sched_grinder *grinder = subport->grinder + pos;
struct rte_sched_pipe *pipe = grinder->pipe;
@@ -2403,8 +2516,16 @@ grinder_schedule(struct rte_sched_port *port,
uint32_t pkt_len = pkt->pkt_len + port->frame_overhead;
uint32_t be_tc_active;
- if (!grinder_credits_check(port, subport, pos))
- return 0;
+ switch (subport->is_tc_ov_enabled) {
+ case 1:
+ if (!grinder_credits_check_with_tc_ov(port, subport, pos))
+ return 0;
+ break;
+ case 0:
+ if (!grinder_credits_check(port, subport, pos))
+ return 0;
+ break;
+ }
/* Advance port time */
port->time += pkt_len;
@@ -2770,7 +2891,11 @@ grinder_handle(struct rte_sched_port *port,
subport->profile;
grinder_prefetch_tc_queue_arrays(subport, pos);
- grinder_credits_update(port, subport, pos);
+
+ if (unlikely(subport->is_tc_ov_enabled))
+ grinder_credits_update_with_tc_ov(port, subport, pos);
+ else
+ grinder_credits_update(port, subport, pos);
grinder->state = e_GRINDER_PREFETCH_MBUF;
return 0;
diff --git a/lib/sched/rte_sched.h b/lib/sched/rte_sched.h
index 5ece64e527..94febe1d94 100644
--- a/lib/sched/rte_sched.h
+++ b/lib/sched/rte_sched.h
@@ -579,6 +579,24 @@ rte_sched_port_enqueue(struct rte_sched_port *port, struct rte_mbuf **pkts, uint
int
rte_sched_port_dequeue(struct rte_sched_port *port, struct rte_mbuf **pkts, uint32_t n_pkts);
+/**
+ * Hierarchical scheduler subport TC OV enable/disable config.
+ * Note that this function is safe to use at runtime
+ * to enable/disable TC OV for subport.
+ *
+ * @param port
+ * Handle to port scheduler instance
+ * @param subport_id
+ * Subport ID
+ * @param tc_ov_enable
+ * Boolean flag to enable/disable TC OV
+ * @return
+ * 0 upon success, error code otherwise
+ */
+__rte_experimental
+int
+rte_sched_subport_tc_ov_config(struct rte_sched_port *port, uint32_t subport_id, bool tc_ov_enable);
+
#ifdef __cplusplus
}
#endif
diff --git a/lib/sched/version.map b/lib/sched/version.map
index d22c07fc9f..c6e994d8df 100644
--- a/lib/sched/version.map
+++ b/lib/sched/version.map
@@ -34,4 +34,7 @@ EXPERIMENTAL {
# added in 21.11
rte_pie_rt_data_init;
rte_pie_config_init;
+
+ # added in 22.03
+ rte_sched_subport_tc_ov_config;
};
--
2.25.1
--------------------------------------------------------------
Intel Research and Development Ireland Limited
Registered in Ireland
Registered Office: Collinstown Industrial Park, Leixlip, County Kildare
Registered Number: 308263
This e-mail and any attachments may contain confidential material for the sole
use of the intended recipient(s). Any review or distribution by others is
strictly prohibited. If you are not the intended recipient, please contact the
sender and delete all copies.
next reply other threads:[~2022-04-27 8:58 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-04-27 8:58 Marcin Danilewicz [this message]
2022-04-27 9:36 ` Dumitrescu, Cristian
2022-04-27 9:37 ` Dumitrescu, Cristian
2022-04-27 15:53 ` Stephen Hemminger
-- strict thread matches above, loose matches on Subject: below --
2022-04-07 14:51 [dpdk][PATCH 2/2] sched: fix to manage " Marcin Danilewicz
2022-04-27 9:23 ` [PATCH v3] sched: enable/disable " Marcin Danilewicz
2022-04-27 15:48 ` Singh, Jasvinder
2022-05-09 20:05 ` Dumitrescu, Cristian
2022-05-10 6:40 ` Ajmera, Megha
2022-05-10 9:09 ` Dumitrescu, Cristian
2022-05-24 13:33 ` Marcin Danilewicz
2022-05-24 14:52 ` Stephen Hemminger
2022-05-26 23:12 ` Danilewicz, MarcinX
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20220427085848.491395-1-marcinx.danilewicz@intel.com \
--to=marcinx.danilewicz@intel.com \
--cc=dev@dpdk.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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).