Add stats for cross-core dispatching scheduler if stats collection is
enabled.
Signed-off-by: Haiyue Wang <haiyue.w...@intel.com>
Signed-off-by: Cunming Liang <cunming.li...@intel.com>
Signed-off-by: Zhirun Yan <zhirun....@intel.com>
---
lib/graph/graph_debug.c | 6 +++
lib/graph/graph_stats.c | 74 +++++++++++++++++++++++++---
lib/graph/rte_graph.h | 2 +
lib/graph/rte_graph_model_dispatch.c | 3 ++
lib/graph/rte_graph_worker_common.h | 2 +
5 files changed, 79 insertions(+), 8 deletions(-)
diff --git a/lib/graph/graph_debug.c b/lib/graph/graph_debug.c
index b84412f5dd..7dcf07b080 100644
--- a/lib/graph/graph_debug.c
+++ b/lib/graph/graph_debug.c
@@ -74,6 +74,12 @@ rte_graph_obj_dump(FILE *f, struct rte_graph *g, bool all)
fprintf(f, " size=%d\n", n->size);
fprintf(f, " idx=%d\n", n->idx);
fprintf(f, " total_objs=%" PRId64 "\n", n->total_objs);
+ if (rte_graph_worker_model_get() ==
RTE_GRAPH_MODEL_MCORE_DISPATCH) {
+ fprintf(f, " total_sched_objs=%" PRId64 "\n",
+ n->total_sched_objs);
+ fprintf(f, " total_sched_fail=%" PRId64 "\n",
+ n->total_sched_fail);
+ }
fprintf(f, " total_calls=%" PRId64 "\n", n->total_calls);
for (i = 0; i < n->nb_edges; i++)
fprintf(f, " edge[%d] <%s>\n", i,
diff --git a/lib/graph/graph_stats.c b/lib/graph/graph_stats.c
index c0140ba922..aa22cc403c 100644
--- a/lib/graph/graph_stats.c
+++ b/lib/graph/graph_stats.c
@@ -40,13 +40,19 @@ struct rte_graph_cluster_stats {
struct cluster_node clusters[];
} __rte_cache_aligned;
+#define boarder_model_dispatch()
\
+ fprintf(f, "+-------------------------------+---------------+--------" \
+ "-------+---------------+---------------+---------------+" \
+ "---------------+---------------+-" \
+ "----------+\n")
+
#define boarder()
\
fprintf(f, "+-------------------------------+---------------+--------" \
"-------+---------------+---------------+---------------+-" \
"----------+\n")
static inline void
-print_banner(FILE *f)
+print_banner_default(FILE *f)
{
boarder();
fprintf(f, "%-32s%-16s%-16s%-16s%-16s%-16s%-16s\n", "|Node", "|calls",
@@ -55,6 +61,27 @@ print_banner(FILE *f)
boarder();
}
+static inline void
+print_banner_dispatch(FILE *f)
+{
+ boarder_model_dispatch();
+ fprintf(f, "%-32s%-16s%-16s%-16s%-16s%-16s%-16s%-16s%-16s\n",
+ "|Node", "|calls",
+ "|objs", "|sched objs", "|sched fail",
+ "|realloc_count", "|objs/call", "|objs/sec(10E6)",
+ "|cycles/call|");
+ boarder_model_dispatch();
+}
+
+static inline void
+print_banner(FILE *f)
+{
+ if (rte_graph_worker_model_get() == RTE_GRAPH_MODEL_MCORE_DISPATCH)
+ print_banner_dispatch(f);
+ else
+ print_banner_default(f);
+}
+
static inline void
print_node(FILE *f, const struct rte_graph_cluster_node_stats *stat)
{
@@ -76,11 +103,21 @@ print_node(FILE *f, const struct
rte_graph_cluster_node_stats *stat)
objs_per_sec = ts_per_hz ? (objs - prev_objs) / ts_per_hz : 0;
objs_per_sec /= 1000000;
- fprintf(f,
- "|%-31s|%-15" PRIu64 "|%-15" PRIu64 "|%-15" PRIu64
- "|%-15.3f|%-15.6f|%-11.4f|\n",
- stat->name, calls, objs, stat->realloc_count, objs_per_call,
- objs_per_sec, cycles_per_call);
+ if (rte_graph_worker_model_get() == RTE_GRAPH_MODEL_MCORE_DISPATCH) {
+ fprintf(f,
+ "|%-31s|%-15" PRIu64 "|%-15" PRIu64 "|%-15" PRIu64
+ "|%-15" PRIu64 "|%-15" PRIu64
+ "|%-15.3f|%-15.6f|%-11.4f|\n",
+ stat->name, calls, objs, stat->sched_objs,
+ stat->sched_fail, stat->realloc_count, objs_per_call,
+ objs_per_sec, cycles_per_call);
+ } else {
+ fprintf(f,
+ "|%-31s|%-15" PRIu64 "|%-15" PRIu64 "|%-15" PRIu64
+ "|%-15.3f|%-15.6f|%-11.4f|\n",
+ stat->name, calls, objs, stat->realloc_count,
objs_per_call,
+ objs_per_sec, cycles_per_call);
+ }
}
static int
@@ -88,13 +125,20 @@ graph_cluster_stats_cb(bool is_first, bool is_last, void
*cookie,
const struct rte_graph_cluster_node_stats *stat)
{
FILE *f = cookie;
+ int model;
+
+ model = rte_graph_worker_model_get();
if (unlikely(is_first))
print_banner(f);
if (stat->objs)
print_node(f, stat);
- if (unlikely(is_last))
- boarder();
+ if (unlikely(is_last)) {
+ if (model == RTE_GRAPH_MODEL_MCORE_DISPATCH)
+ boarder_model_dispatch();
+ else
+ boarder();
+ }
return 0;
};
@@ -332,13 +376,21 @@ static inline void
cluster_node_arregate_stats(struct cluster_node *cluster)
{
uint64_t calls = 0, cycles = 0, objs = 0, realloc_count = 0;
+ uint64_t sched_objs = 0, sched_fail = 0;
struct rte_graph_cluster_node_stats *stat = &cluster->stat;
struct rte_node *node;
rte_node_t count;
+ int model;
+ model = rte_graph_worker_model_get();
for (count = 0; count < cluster->nb_nodes; count++) {
node = cluster->nodes[count];
+ if (model == RTE_GRAPH_MODEL_MCORE_DISPATCH) {
+ sched_objs += node->total_sched_objs;
+ sched_fail += node->total_sched_fail;
+ }
+
calls += node->total_calls;
objs += node->total_objs;
cycles += node->total_cycles;
@@ -348,6 +400,12 @@ cluster_node_arregate_stats(struct cluster_node *cluster)
stat->calls = calls;
stat->objs = objs;
stat->cycles = cycles;
+
+ if (model == RTE_GRAPH_MODEL_MCORE_DISPATCH) {
+ stat->sched_objs = sched_objs;
+ stat->sched_fail = sched_fail;
+ }
+
stat->ts = rte_get_timer_cycles();
stat->realloc_count = realloc_count;
}
diff --git a/lib/graph/rte_graph.h b/lib/graph/rte_graph.h
index 2f86c17de7..7d77a790ac 100644
--- a/lib/graph/rte_graph.h
+++ b/lib/graph/rte_graph.h
@@ -208,6 +208,8 @@ struct rte_graph_cluster_node_stats {
uint64_t prev_calls; /**< Previous number of calls. */
uint64_t prev_objs; /**< Previous number of processed objs. */
uint64_t prev_cycles; /**< Previous number of cycles. */
+ uint64_t sched_objs; /**< Previous number of scheduled objs. */
+ uint64_t sched_fail; /**< Previous number of failed schedule objs. */
uint64_t realloc_count; /**< Realloc count. */
diff --git a/lib/graph/rte_graph_model_dispatch.c
b/lib/graph/rte_graph_model_dispatch.c
index a300fefb85..9db60eb463 100644
--- a/lib/graph/rte_graph_model_dispatch.c
+++ b/lib/graph/rte_graph_model_dispatch.c
@@ -83,6 +83,7 @@ __graph_sched_node_enqueue(struct rte_node *node, struct
rte_graph *graph)
rte_pause();
off += size;
+ node->total_sched_objs += size;
node->idx -= size;
if (node->idx > 0)
goto submit_again;
@@ -94,6 +95,8 @@ __graph_sched_node_enqueue(struct rte_node *node, struct
rte_graph *graph)
memmove(&node->objs[0], &node->objs[off],
node->idx * sizeof(void *));
+ node->total_sched_fail += node->idx;
+
return false;
}
diff --git a/lib/graph/rte_graph_worker_common.h
b/lib/graph/rte_graph_worker_common.h
index dc0a0b5554..d94983589c 100644
--- a/lib/graph/rte_graph_worker_common.h
+++ b/lib/graph/rte_graph_worker_common.h
@@ -95,6 +95,8 @@ struct rte_node {
/* Fast schedule area for mcore dispatch model */
unsigned int lcore_id; /**< Node running lcore. */
};
+ uint64_t total_sched_objs; /**< Number of objects scheduled. */
+ uint64_t total_sched_fail; /**< Number of scheduled failure. */
/* Fast path area */
#define RTE_NODE_CTX_SZ 16
uint8_t ctx[RTE_NODE_CTX_SZ] __rte_cache_aligned; /**< Node Context. */
--
2.37.2
