[v9,2/5] eal: report applications lcore usage

Message ID 20230207193731.1242505-3-rjarry@redhat.com (mailing list archive)
State Not Applicable, archived
Delegated to: David Marchand
Headers
Series None |

Checks

Context Check Description
ci/iol-testing warning apply patch failure
ci/Intel-compilation warning apply issues

Commit Message

Robin Jarry Feb. 7, 2023, 7:37 p.m. UTC
  Allow applications to register a callback that will be invoked in
rte_lcore_dump() and when requesting lcore info in the telemetry API.

The callback is expected to return the number of TSC cycles that have
passed since application start and the number of these cycles that were
spent doing busy work.

Signed-off-by: Robin Jarry <rjarry@redhat.com>
Acked-by: Morten Brørup <mb@smartsharesystems.com>
Reviewed-by: Kevin Laatz <kevin.laatz@intel.com>
---

Notes:
    v8 -> v9:
    
    - Fixed changelog & version.map order.
    - Updated with 64-bit integer telemetry functions.
    - Refined docstrings (added notice about resetting the callback).

 doc/guides/rel_notes/release_23_03.rst |  7 ++++
 lib/eal/common/eal_common_lcore.c      | 40 +++++++++++++++++++--
 lib/eal/include/rte_lcore.h            | 48 ++++++++++++++++++++++++++
 lib/eal/version.map                    |  1 +
 4 files changed, 94 insertions(+), 2 deletions(-)
  

Patch

diff --git a/doc/guides/rel_notes/release_23_03.rst b/doc/guides/rel_notes/release_23_03.rst
index 1fa101c420cd..17d38d5ea264 100644
--- a/doc/guides/rel_notes/release_23_03.rst
+++ b/doc/guides/rel_notes/release_23_03.rst
@@ -55,6 +55,13 @@  New Features
      Also, make sure to start the actual text at the margin.
      =======================================================
 
+* **Added support for reporting lcore usage in applications.**
+
+  * The ``/eal/lcore/list`` and ``/eal/lcore/info`` telemetry endpoints have
+    been added to provide information similar to ``rte_lcore_dump()``.
+  * Applications can register a callback at startup via
+    ``rte_lcore_register_usage_cb()`` to provide lcore usage information.
+
 * **Updated AMD axgbe driver.**
 
   * Added multi-process support.
diff --git a/lib/eal/common/eal_common_lcore.c b/lib/eal/common/eal_common_lcore.c
index f53fc17b4d04..fcda7c50119a 100644
--- a/lib/eal/common/eal_common_lcore.c
+++ b/lib/eal/common/eal_common_lcore.c
@@ -2,6 +2,7 @@ 
  * Copyright(c) 2010-2014 Intel Corporation
  */
 
+#include <inttypes.h>
 #include <stdlib.h>
 #include <string.h>
 
@@ -437,20 +438,45 @@  lcore_role_str(enum rte_lcore_role_t role)
 	}
 }
 
+static rte_lcore_usage_cb lcore_usage_cb;
+
+void
+rte_lcore_register_usage_cb(rte_lcore_usage_cb cb)
+{
+	lcore_usage_cb = cb;
+}
+
 static int
 lcore_dump_cb(unsigned int lcore_id, void *arg)
 {
 	struct rte_config *cfg = rte_eal_get_configuration();
 	char cpuset[RTE_CPU_AFFINITY_STR_LEN];
+	struct rte_lcore_usage usage;
+	rte_lcore_usage_cb usage_cb;
+	char *usage_str = NULL;
 	FILE *f = arg;
 	int ret;
 
+	/* The callback may not set all the fields in the structure, so clear it here. */
+	memset(&usage, 0, sizeof(usage));
+	/* Guard against concurrent modification of lcore_usage_cb. */
+	usage_cb = lcore_usage_cb;
+	if (usage_cb != NULL && usage_cb(lcore_id, &usage) == 0) {
+		if (asprintf(&usage_str, ", busy cycles %"PRIu64"/%"PRIu64,
+				usage.busy_cycles, usage.total_cycles) < 0) {
+			return -ENOMEM;
+		}
+	}
 	ret = eal_thread_dump_affinity(&lcore_config[lcore_id].cpuset, cpuset,
 		sizeof(cpuset));
-	fprintf(f, "lcore %u, socket %u, role %s, cpuset %s%s\n", lcore_id,
+	fprintf(f, "lcore %u, socket %u, role %s, cpuset %s%s%s\n", lcore_id,
 		rte_lcore_to_socket_id(lcore_id),
 		lcore_role_str(cfg->lcore_role[lcore_id]),
-		cpuset, ret == 0 ? "" : "...");
+		cpuset, ret == 0 ? "" : "...",
+		usage_str != NULL ? usage_str : "");
+
+	free(usage_str);
+
 	return 0;
 }
 
@@ -489,7 +515,9 @@  lcore_telemetry_info_cb(unsigned int lcore_id, void *arg)
 {
 	struct rte_config *cfg = rte_eal_get_configuration();
 	struct lcore_telemetry_info *info = arg;
+	struct rte_lcore_usage usage;
 	struct rte_tel_data *cpuset;
+	rte_lcore_usage_cb usage_cb;
 	unsigned int cpu;
 
 	if (info->lcore_id != lcore_id)
@@ -508,6 +536,14 @@  lcore_telemetry_info_cb(unsigned int lcore_id, void *arg)
 			rte_tel_data_add_array_int(cpuset, cpu);
 	}
 	rte_tel_data_add_dict_container(info->d, "cpuset", cpuset, 0);
+	/* The callback may not set all the fields in the structure, so clear it here. */
+	memset(&usage, 0, sizeof(usage));
+	/* Guard against concurrent modification of lcore_usage_cb. */
+	usage_cb = lcore_usage_cb;
+	if (usage_cb != NULL && usage_cb(lcore_id, &usage) == 0) {
+		rte_tel_data_add_dict_uint(info->d, "total_cycles", usage.total_cycles);
+		rte_tel_data_add_dict_uint(info->d, "busy_cycles", usage.busy_cycles);
+	}
 
 	return 0;
 }
diff --git a/lib/eal/include/rte_lcore.h b/lib/eal/include/rte_lcore.h
index 9c7865052100..30f83f4d578c 100644
--- a/lib/eal/include/rte_lcore.h
+++ b/lib/eal/include/rte_lcore.h
@@ -328,6 +328,54 @@  typedef int (*rte_lcore_iterate_cb)(unsigned int lcore_id, void *arg);
 int
 rte_lcore_iterate(rte_lcore_iterate_cb cb, void *arg);
 
+/**
+ * lcore usage statistics.
+ */
+struct rte_lcore_usage {
+	/**
+	 * The total amount of time that the application has been running on
+	 * this lcore, in TSC cycles.
+	 */
+	uint64_t total_cycles;
+	/**
+	 * The amount of time the application was busy, handling some
+	 * workload on this lcore, in TSC cycles.
+	 */
+	uint64_t busy_cycles;
+};
+
+/**
+ * Callback to allow applications to report lcore usage.
+ *
+ * @param [in] lcore_id
+ *   The lcore to consider.
+ * @param [out] usage
+ *   Counters representing this lcore usage. This can never be NULL.
+ * @return
+ *   - 0 if fields in usage were updated successfully. The fields that the
+ *       application does not support must not be modified.
+ *   - a negative value if the information is not available or if any error occurred.
+ */
+typedef int (*rte_lcore_usage_cb)(unsigned int lcore_id, struct rte_lcore_usage *usage);
+
+/**
+ * @warning
+ * @b EXPERIMENTAL: this API may change without prior notice.
+ *
+ * Register a callback from an application to be called in rte_lcore_dump() and
+ * the /eal/lcore/info telemetry endpoint handler. Applications are expected to
+ * report lcore usage statistics via this callback.
+ *
+ * If a callback was already registered, it can be replaced with another callback
+ * or unregistered with NULL. The previously registered callback may remain in
+ * use for an undetermined period of time.
+ *
+ * @param cb
+ *   The callback function.
+ */
+__rte_experimental
+void rte_lcore_register_usage_cb(rte_lcore_usage_cb cb);
+
 /**
  * List all lcores.
  *
diff --git a/lib/eal/version.map b/lib/eal/version.map
index 6523102157e2..2c05e5f2fb60 100644
--- a/lib/eal/version.map
+++ b/lib/eal/version.map
@@ -441,6 +441,7 @@  EXPERIMENTAL {
 	rte_thread_join;
 
 	# added in 23.03
+	rte_lcore_register_usage_cb;
 	rte_thread_set_name;
 };