vdpa/mlx5: add CPU core parameter to bind polling thread

This patch adds new device argument to specify cpu core affinity to
event polling thread for better latency and throughput. The thread
could be also located by name "vDPA-mlx5-<id>".

Signed-off-by: Xueming Li <xuemingl@nvidia.com>
Acked-by: Matan Azrad <matan@nvidia.com>
Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com>

diff --git a/doc/guides/vdpadevs/mlx5.rst b/doc/guides/vdpadevs/mlx5.rst
index 903fdb0..2025425 100644 (file)
--- a/doc/guides/vdpadevs/mlx5.rst
+++ b/doc/guides/vdpadevs/mlx5.rst
@@ -134,6 +134,11 @@ Driver options
   interrupts are configured to the device in order to notify traffic for the
   driver. Default value is 2s.
 
   interrupts are configured to the device in order to notify traffic for the
   driver. Default value is 2s.
 

+- ``event_core`` parameter [int]
+
+  CPU core number to set polling thread affinity to, default to control plane
+  cpu.
+

 Error handling
 ^^^^^^^^^^^^^^
 
 Error handling
 ^^^^^^^^^^^^^^
 

diff --git a/drivers/vdpa/mlx5/mlx5_vdpa.c b/drivers/vdpa/mlx5/mlx5_vdpa.c
index 5020a99..1f92c52 100644 (file)
--- a/drivers/vdpa/mlx5/mlx5_vdpa.c
+++ b/drivers/vdpa/mlx5/mlx5_vdpa.c
@@ -612,6 +612,7 @@ mlx5_vdpa_args_check_handler(const char *key, const char *val, void *opaque)
 {
        struct mlx5_vdpa_priv *priv = opaque;
        unsigned long tmp;
 {
        struct mlx5_vdpa_priv *priv = opaque;
        unsigned long tmp;

+       int n_cores = sysconf(_SC_NPROCESSORS_ONLN);

 
        if (strcmp(key, "class") == 0)
                return 0;
 
        if (strcmp(key, "class") == 0)
                return 0;


@@ -630,6 +631,11 @@ mlx5_vdpa_args_check_handler(const char *key, const char *val, void *opaque)
                priv->event_us = (uint32_t)tmp;
        } else if (strcmp(key, "no_traffic_time") == 0) {
                priv->no_traffic_time_s = (uint32_t)tmp;
                priv->event_us = (uint32_t)tmp;
        } else if (strcmp(key, "no_traffic_time") == 0) {
                priv->no_traffic_time_s = (uint32_t)tmp;

+       } else if (strcmp(key, "event_core") == 0) {
+               if (tmp >= (unsigned long)n_cores)
+                       DRV_LOG(WARNING, "Invalid event_core %s.", val);
+               else
+                       priv->event_core = tmp;

        } else {
                DRV_LOG(WARNING, "Invalid key %s.", key);
        }
        } else {
                DRV_LOG(WARNING, "Invalid key %s.", key);
        }


@@ -643,6 +649,7 @@ mlx5_vdpa_config_get(struct rte_devargs *devargs, struct mlx5_vdpa_priv *priv)
 
        priv->event_mode = MLX5_VDPA_EVENT_MODE_DYNAMIC_TIMER;
        priv->event_us = 0;
 
        priv->event_mode = MLX5_VDPA_EVENT_MODE_DYNAMIC_TIMER;
        priv->event_us = 0;

+       priv->event_core = -1;

        priv->no_traffic_time_s = MLX5_VDPA_DEFAULT_NO_TRAFFIC_TIME_S;
        if (devargs == NULL)
                return;
        priv->no_traffic_time_s = MLX5_VDPA_DEFAULT_NO_TRAFFIC_TIME_S;
        if (devargs == NULL)
                return;

diff --git a/drivers/vdpa/mlx5/mlx5_vdpa.h b/drivers/vdpa/mlx5/mlx5_vdpa.h
index 08e04a8..b4dd383 100644 (file)
--- a/drivers/vdpa/mlx5/mlx5_vdpa.h
+++ b/drivers/vdpa/mlx5/mlx5_vdpa.h
@@ -131,6 +131,7 @@ struct mlx5_vdpa_priv {
        pthread_cond_t timer_cond;
        volatile uint8_t timer_on;
        int event_mode;
        pthread_cond_t timer_cond;
        volatile uint8_t timer_on;
        int event_mode;

+       int event_core; /* Event thread cpu affinity core. */

        uint32_t event_us;
        uint32_t timer_delay_us;
        uint32_t no_traffic_time_s;
        uint32_t event_us;
        uint32_t timer_delay_us;
        uint32_t no_traffic_time_s;

diff --git a/drivers/vdpa/mlx5/mlx5_vdpa_event.c b/drivers/vdpa/mlx5/mlx5_vdpa_event.c
index d108ca9..a055d20 100644 (file)
--- a/drivers/vdpa/mlx5/mlx5_vdpa_event.c
+++ b/drivers/vdpa/mlx5/mlx5_vdpa_event.c
@@ -533,6 +533,9 @@ int
 mlx5_vdpa_cqe_event_setup(struct mlx5_vdpa_priv *priv)
 {
        int ret;
 mlx5_vdpa_cqe_event_setup(struct mlx5_vdpa_priv *priv)
 {
        int ret;

+       rte_cpuset_t cpuset;
+       pthread_attr_t attr;
+       char name[16];

 
        if (!priv->eventc)
                /* All virtqs are in poll mode. */
 
        if (!priv->eventc)
                /* All virtqs are in poll mode. */


@@ -541,12 +544,30 @@ mlx5_vdpa_cqe_event_setup(struct mlx5_vdpa_priv *priv)
                pthread_mutex_init(&priv->timer_lock, NULL);
                pthread_cond_init(&priv->timer_cond, NULL);
                priv->timer_on = 0;
                pthread_mutex_init(&priv->timer_lock, NULL);
                pthread_cond_init(&priv->timer_cond, NULL);
                priv->timer_on = 0;

-               ret = pthread_create(&priv->timer_tid, NULL,
+               pthread_attr_init(&attr);
+               CPU_ZERO(&cpuset);
+               if (priv->event_core != -1)
+                       CPU_SET(priv->event_core, &cpuset);
+               else
+                       cpuset = rte_lcore_cpuset(rte_get_main_lcore());
+               ret = pthread_attr_setaffinity_np(&attr, sizeof(cpuset),
+                                                 &cpuset);
+               if (ret) {
+                       DRV_LOG(ERR, "Failed to set thread affinity.");
+                       return -1;
+               }
+               ret = pthread_create(&priv->timer_tid, &attr,

                                     mlx5_vdpa_poll_handle, (void *)priv);
                if (ret) {
                        DRV_LOG(ERR, "Failed to create timer thread.");
                        return -1;
                }
                                     mlx5_vdpa_poll_handle, (void *)priv);
                if (ret) {
                        DRV_LOG(ERR, "Failed to create timer thread.");
                        return -1;
                }

+               snprintf(name, sizeof(name), "vDPA-mlx5-%d", priv->vid);
+               ret = pthread_setname_np(priv->timer_tid, name);
+               if (ret) {
+                       DRV_LOG(ERR, "Failed to set timer thread name.");
+                       return -1;
+               }

        }
        priv->intr_handle.fd = priv->eventc->fd;
        priv->intr_handle.type = RTE_INTR_HANDLE_EXT;
        }
        priv->intr_handle.fd = priv->eventc->fd;
        priv->intr_handle.type = RTE_INTR_HANDLE_EXT;