[v2,1/2] eal: add API that sleeps while waiting for threads
Checks
Commit Message
It is common that sample applications call rte_eal_wait_lcore() while
waiting for worker threads to be terminated.
Mostly master lcore keeps waiting in this function.
The waiting app for termination is not a time critical task, app can
prefer a sleep version of the waiting to consume less cycles.
A sleeping version of the API, rte_eal_wait_lcore_sleep(), has been
added which uses pthread conditions.
Sample applications will be updated later to use this API.
Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
---
v2:
* use pthread cond instead of usleep
---
lib/librte_eal/bsdapp/eal/eal.c | 3 +++
lib/librte_eal/bsdapp/eal/eal_thread.c | 7 ++++++
lib/librte_eal/common/eal_common_launch.c | 22 ++++++++++++++++++
lib/librte_eal/common/include/rte_launch.h | 26 ++++++++++++++++++++++
lib/librte_eal/common/include/rte_lcore.h | 3 +++
lib/librte_eal/linuxapp/eal/eal.c | 3 +++
lib/librte_eal/linuxapp/eal/eal_thread.c | 7 ++++++
lib/librte_eal/rte_eal_version.map | 1 +
8 files changed, 72 insertions(+)
Comments
HI Ferruh,
> -----Original Message-----
> From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Ferruh Yigit
> Sent: Monday, October 15, 2018 11:21 PM
> To: Richardson, Bruce <bruce.richardson@intel.com>
> Cc: dev@dpdk.org; Yigit, Ferruh <ferruh.yigit@intel.com>; stephen@networkplumber.org
> Subject: [dpdk-dev] [PATCH v2 1/2] eal: add API that sleeps while waiting for threads
>
> It is common that sample applications call rte_eal_wait_lcore() while
> waiting for worker threads to be terminated.
> Mostly master lcore keeps waiting in this function.
>
> The waiting app for termination is not a time critical task, app can
> prefer a sleep version of the waiting to consume less cycles.
>
> A sleeping version of the API, rte_eal_wait_lcore_sleep(), has been
> added which uses pthread conditions.
>
> Sample applications will be updated later to use this API.
>
> Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
> ---
> v2:
> * use pthread cond instead of usleep
> ---
> lib/librte_eal/bsdapp/eal/eal.c | 3 +++
> lib/librte_eal/bsdapp/eal/eal_thread.c | 7 ++++++
> lib/librte_eal/common/eal_common_launch.c | 22 ++++++++++++++++++
> lib/librte_eal/common/include/rte_launch.h | 26 ++++++++++++++++++++++
> lib/librte_eal/common/include/rte_lcore.h | 3 +++
> lib/librte_eal/linuxapp/eal/eal.c | 3 +++
> lib/librte_eal/linuxapp/eal/eal_thread.c | 7 ++++++
> lib/librte_eal/rte_eal_version.map | 1 +
> 8 files changed, 72 insertions(+)
>
> diff --git a/lib/librte_eal/bsdapp/eal/eal.c b/lib/librte_eal/bsdapp/eal/eal.c
> index 7735194a3..e7d676657 100644
> --- a/lib/librte_eal/bsdapp/eal/eal.c
> +++ b/lib/librte_eal/bsdapp/eal/eal.c
> @@ -756,6 +756,9 @@ rte_eal_init(int argc, char **argv)
> snprintf(thread_name, sizeof(thread_name),
> "lcore-slave-%d", i);
> rte_thread_setname(lcore_config[i].thread_id, thread_name);
> +
> + pthread_mutex_init(&rte_eal_thread_mutex[i], NULL);
> + pthread_cond_init(&rte_eal_thread_cond[i], NULL);
> }
>
> /*
> diff --git a/lib/librte_eal/bsdapp/eal/eal_thread.c b/lib/librte_eal/bsdapp/eal/eal_thread.c
> index 309b58726..60db32d57 100644
> --- a/lib/librte_eal/bsdapp/eal/eal_thread.c
> +++ b/lib/librte_eal/bsdapp/eal/eal_thread.c
> @@ -28,6 +28,9 @@ RTE_DEFINE_PER_LCORE(unsigned, _lcore_id) = LCORE_ID_ANY;
> RTE_DEFINE_PER_LCORE(unsigned, _socket_id) = (unsigned)SOCKET_ID_ANY;
> RTE_DEFINE_PER_LCORE(rte_cpuset_t, _cpuset);
>
> +pthread_cond_t rte_eal_thread_cond[RTE_MAX_LCORE];
> +pthread_mutex_t rte_eal_thread_mutex[RTE_MAX_LCORE];
I think would be better to include cond and mutex into struct lcore_config itself,
probably would help to avoid false sharing.
Though yeh, it would mean ABI breakage, I suppose.
> +
> /*
> * Send a message to a slave lcore identified by slave_id to call a
> * function f with argument arg. Once the execution is done, the
> @@ -154,6 +157,10 @@ eal_thread_loop(__attribute__((unused)) void *arg)
> lcore_config[lcore_id].ret = ret;
> rte_wmb();
> lcore_config[lcore_id].state = FINISHED;
> +
> + pthread_mutex_lock(&rte_eal_thread_mutex[lcore_id]);
> + pthread_cond_signal(&rte_eal_thread_cond[lcore_id]);
> + pthread_mutex_unlock(&rte_eal_thread_mutex[lcore_id]);
I understand it would work that way too, but if you introduce mutex and cond around
the state, then it is better to manipulate/access the state after grabbing the mutex.
BTW in that case we don't need wmb:
lcore_config[lcore_id].ret = ret;
pthread_mutex_lock(...);
lcore_config[lcore_id].state = FINISHED;
pthread_cond_signal(..);
pthread_mutex_unlock(...);
Konstantin
>
> +/*
> + * Wait until a lcore finished its job by pthread condition.
> + */
> +int
> +rte_eal_wait_lcore_sleep(unsigned slave_id)
> +{
> + if (lcore_config[slave_id].state == WAIT)
> + return 0;
> +
> + pthread_mutex_lock(&rte_eal_thread_mutex[slave_id]);
> + while (lcore_config[slave_id].state != WAIT &&
> + lcore_config[slave_id].state != FINISHED)
> + pthread_cond_wait(&rte_eal_thread_cond[slave_id],
> + &rte_eal_thread_mutex[slave_id]);
> + pthread_mutex_unlock(&rte_eal_thread_mutex[slave_id]);
> +
> + /* we are in finished state, go to wait state */
> + lcore_config[slave_id].state = WAIT;
> + return lcore_config[slave_id].ret;
> +}
> +
Actually, another question - could that 2 or more threads wait for the same core simultaneously?
If yes, then 2-nd thread in that function might stuck forever.
In that case it is better to use cond_timed_wait() here and cond_broadcast() above.
Konstantin
@@ -756,6 +756,9 @@ rte_eal_init(int argc, char **argv)
snprintf(thread_name, sizeof(thread_name),
"lcore-slave-%d", i);
rte_thread_setname(lcore_config[i].thread_id, thread_name);
+
+ pthread_mutex_init(&rte_eal_thread_mutex[i], NULL);
+ pthread_cond_init(&rte_eal_thread_cond[i], NULL);
}
/*
@@ -28,6 +28,9 @@ RTE_DEFINE_PER_LCORE(unsigned, _lcore_id) = LCORE_ID_ANY;
RTE_DEFINE_PER_LCORE(unsigned, _socket_id) = (unsigned)SOCKET_ID_ANY;
RTE_DEFINE_PER_LCORE(rte_cpuset_t, _cpuset);
+pthread_cond_t rte_eal_thread_cond[RTE_MAX_LCORE];
+pthread_mutex_t rte_eal_thread_mutex[RTE_MAX_LCORE];
+
/*
* Send a message to a slave lcore identified by slave_id to call a
* function f with argument arg. Once the execution is done, the
@@ -154,6 +157,10 @@ eal_thread_loop(__attribute__((unused)) void *arg)
lcore_config[lcore_id].ret = ret;
rte_wmb();
lcore_config[lcore_id].state = FINISHED;
+
+ pthread_mutex_lock(&rte_eal_thread_mutex[lcore_id]);
+ pthread_cond_signal(&rte_eal_thread_cond[lcore_id]);
+ pthread_mutex_unlock(&rte_eal_thread_mutex[lcore_id]);
}
/* never reached */
@@ -5,6 +5,7 @@
#include <errno.h>
#include <stdint.h>
#include <stdio.h>
+#include <unistd.h>
#include <sys/queue.h>
#include <rte_launch.h>
@@ -35,6 +36,27 @@ rte_eal_wait_lcore(unsigned slave_id)
return lcore_config[slave_id].ret;
}
+/*
+ * Wait until a lcore finished its job by pthread condition.
+ */
+int
+rte_eal_wait_lcore_sleep(unsigned slave_id)
+{
+ if (lcore_config[slave_id].state == WAIT)
+ return 0;
+
+ pthread_mutex_lock(&rte_eal_thread_mutex[slave_id]);
+ while (lcore_config[slave_id].state != WAIT &&
+ lcore_config[slave_id].state != FINISHED)
+ pthread_cond_wait(&rte_eal_thread_cond[slave_id],
+ &rte_eal_thread_mutex[slave_id]);
+ pthread_mutex_unlock(&rte_eal_thread_mutex[slave_id]);
+
+ /* we are in finished state, go to wait state */
+ lcore_config[slave_id].state = WAIT;
+ return lcore_config[slave_id].ret;
+}
+
/*
* Check that every SLAVE lcores are in WAIT state, then call
* rte_eal_remote_launch() for all of them. If call_master is true
@@ -11,6 +11,8 @@
* Launch tasks on other lcores
*/
+#include <rte_compat.h>
+
#ifdef __cplusplus
extern "C" {
#endif
@@ -129,6 +131,30 @@ enum rte_lcore_state_t rte_eal_get_lcore_state(unsigned slave_id);
*/
int rte_eal_wait_lcore(unsigned slave_id);
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice
+ *
+ * Wait until an lcore finishes its job.
+ *
+ * To be executed on the MASTER lcore only.
+ *
+ * Same as rte_eal_wait_lcore() but waits using pthread conditions
+ * instead of polling in busy loop.
+ *
+ * @param slave_id
+ * The identifier of the lcore.
+ * @return
+ * - 0: If the lcore identified by the slave_id is in a WAIT state.
+ * - The value that was returned by the previous remote launch
+ * function call if the lcore identified by the slave_id was in a
+ * FINISHED or RUNNING state. In this case, it changes the state
+ * of the lcore to WAIT.
+ */
+__rte_experimental int
+rte_eal_wait_lcore_sleep(unsigned slave_id);
+
/**
* Wait until all lcores finish their jobs.
*
@@ -53,6 +53,9 @@ struct lcore_config {
*/
extern struct lcore_config lcore_config[RTE_MAX_LCORE];
+extern pthread_cond_t rte_eal_thread_cond[RTE_MAX_LCORE];
+extern pthread_mutex_t rte_eal_thread_mutex[RTE_MAX_LCORE];
+
RTE_DECLARE_PER_LCORE(unsigned, _lcore_id); /**< Per thread "lcore id". */
RTE_DECLARE_PER_LCORE(rte_cpuset_t, _cpuset); /**< Per thread "cpuset". */
@@ -1019,6 +1019,9 @@ rte_eal_init(int argc, char **argv)
lcore_config[i].state = WAIT;
+ pthread_mutex_init(&rte_eal_thread_mutex[i], NULL);
+ pthread_cond_init(&rte_eal_thread_cond[i], NULL);
+
/* create a thread for each lcore */
ret = pthread_create(&lcore_config[i].thread_id, NULL,
eal_thread_loop, NULL);
@@ -28,6 +28,9 @@ RTE_DEFINE_PER_LCORE(unsigned, _lcore_id) = LCORE_ID_ANY;
RTE_DEFINE_PER_LCORE(unsigned, _socket_id) = (unsigned)SOCKET_ID_ANY;
RTE_DEFINE_PER_LCORE(rte_cpuset_t, _cpuset);
+pthread_cond_t rte_eal_thread_cond[RTE_MAX_LCORE];
+pthread_mutex_t rte_eal_thread_mutex[RTE_MAX_LCORE];
+
/*
* Send a message to a slave lcore identified by slave_id to call a
* function f with argument arg. Once the execution is done, the
@@ -161,6 +164,10 @@ eal_thread_loop(__attribute__((unused)) void *arg)
lcore_config[lcore_id].state = WAIT;
else
lcore_config[lcore_id].state = FINISHED;
+
+ pthread_mutex_lock(&rte_eal_thread_mutex[lcore_id]);
+ pthread_cond_signal(&rte_eal_thread_cond[lcore_id]);
+ pthread_mutex_unlock(&rte_eal_thread_mutex[lcore_id]);
}
/* never reached */
@@ -292,6 +292,7 @@ EXPERIMENTAL {
rte_devargs_remove;
rte_devargs_type_count;
rte_eal_cleanup;
+ rte_eal_wait_lcore_sleep;
rte_fbarray_attach;
rte_fbarray_destroy;
rte_fbarray_detach;