[RESEND,v9,5/5] eal: add lcore usage telemetry endpoint

Message ID 20230208084507.1328625-6-rjarry@redhat.com (mailing list archive)
State Superseded, archived
Delegated to: David Marchand
Headers
Series lcore telemetry improvements |

Checks

Context Check Description
ci/iol-mellanox-Performance success Performance Testing PASS
ci/iol-broadcom-Functional success Functional Testing PASS
ci/iol-broadcom-Performance fail Performance Testing issues
ci/github-robot: build success github build: passed
ci/iol-intel-Performance success Performance Testing PASS
ci/iol-aarch64-unit-testing success Testing PASS
ci/Intel-compilation success Compilation OK
ci/intel-Testing success Testing PASS
ci/iol-intel-Functional success Functional Testing PASS
ci/loongarch-compilation success Compilation OK
ci/loongarch-unit-testing success Unit Testing PASS
ci/iol-testing success Testing PASS
ci/iol-x86_64-unit-testing success Testing PASS
ci/iol-x86_64-compile-testing success Testing PASS
ci/iol-aarch64-compile-testing success Testing PASS
ci/iol-abi-testing success Testing PASS

Commit Message

Robin Jarry Feb. 8, 2023, 8:45 a.m. UTC
  Allow fetching CPU cycles usage for all lcores with a single request.
This endpoint is intended for repeated and frequent invocations by
external monitoring systems and therefore returns condensed data.

It consists of a single dictionary with three keys: "lcore_ids",
"total_cycles" and "busy_cycles" that are mapped to three arrays of
integer values. Each array has the same number of values, one per lcore,
in the same order.

Example:

 --> /eal/lcore/usage
 {
   "/eal/lcore/usage": {
     "lcore_ids": [
       4,
       5
     ],
     "total_cycles": [
       23846845590,
       23900558914
     ],
     "busy_cycles": [
       21043446682,
       21448837316
     ]
   }
 }

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

Notes:
    v8 -> v9: Updated with 64 bits integer telemetry functions

 doc/guides/rel_notes/release_23_03.rst |  5 ++-
 lib/eal/common/eal_common_lcore.c      | 60 ++++++++++++++++++++++++++
 2 files changed, 63 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 17d38d5ea264..4f2878846829 100644
--- a/doc/guides/rel_notes/release_23_03.rst
+++ b/doc/guides/rel_notes/release_23_03.rst
@@ -57,8 +57,9 @@  New Features
 
 * **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()``.
+  * The ``/eal/lcore/list``, ``/eal/lcore/usage`` 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.
 
diff --git a/lib/eal/common/eal_common_lcore.c b/lib/eal/common/eal_common_lcore.c
index fcda7c50119a..088adb14b4b6 100644
--- a/lib/eal/common/eal_common_lcore.c
+++ b/lib/eal/common/eal_common_lcore.c
@@ -569,6 +569,63 @@  handle_lcore_info(const char *cmd __rte_unused, const char *params, struct rte_t
 	return rte_lcore_iterate(lcore_telemetry_info_cb, &info);
 }
 
+struct lcore_telemetry_usage {
+	struct rte_tel_data *lcore_ids;
+	struct rte_tel_data *total_cycles;
+	struct rte_tel_data *busy_cycles;
+};
+
+static int
+lcore_telemetry_usage_cb(unsigned int lcore_id, void *arg)
+{
+	struct lcore_telemetry_usage *u = arg;
+	struct rte_lcore_usage usage;
+	rte_lcore_usage_cb usage_cb;
+
+	/* 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_array_uint(u->lcore_ids, lcore_id);
+		rte_tel_data_add_array_uint(u->total_cycles, usage.total_cycles);
+		rte_tel_data_add_array_uint(u->busy_cycles, usage.busy_cycles);
+	}
+
+	return 0;
+}
+
+static int
+handle_lcore_usage(const char *cmd __rte_unused,
+		const char *params __rte_unused,
+		struct rte_tel_data *d)
+{
+	struct lcore_telemetry_usage usage;
+	struct rte_tel_data *lcore_ids = rte_tel_data_alloc();
+	struct rte_tel_data *total_cycles = rte_tel_data_alloc();
+	struct rte_tel_data *busy_cycles = rte_tel_data_alloc();
+
+	if (!lcore_ids || !total_cycles || !busy_cycles) {
+		rte_tel_data_free(lcore_ids);
+		rte_tel_data_free(total_cycles);
+		rte_tel_data_free(busy_cycles);
+		return -ENOMEM;
+	}
+
+	rte_tel_data_start_dict(d);
+	rte_tel_data_start_array(lcore_ids, RTE_TEL_UINT_VAL);
+	rte_tel_data_start_array(total_cycles, RTE_TEL_UINT_VAL);
+	rte_tel_data_start_array(busy_cycles, RTE_TEL_UINT_VAL);
+	rte_tel_data_add_dict_container(d, "lcore_ids", lcore_ids, 0);
+	rte_tel_data_add_dict_container(d, "total_cycles", total_cycles, 0);
+	rte_tel_data_add_dict_container(d, "busy_cycles", busy_cycles, 0);
+	usage.lcore_ids = lcore_ids;
+	usage.total_cycles = total_cycles;
+	usage.busy_cycles = busy_cycles;
+
+	return rte_lcore_iterate(lcore_telemetry_usage_cb, &usage);
+}
+
 RTE_INIT(lcore_telemetry)
 {
 	rte_telemetry_register_cmd(
@@ -577,5 +634,8 @@  RTE_INIT(lcore_telemetry)
 	rte_telemetry_register_cmd(
 		"/eal/lcore/info", handle_lcore_info,
 		"Returns lcore info. Parameters: int lcore_id");
+	rte_telemetry_register_cmd(
+		"/eal/lcore/usage", handle_lcore_usage,
+		"Returns lcore cycles usage. Takes no parameters");
 }
 #endif /* !RTE_EXEC_ENV_WINDOWS */