[v8,1/5] eal: add lcore info in telemetry

Message ID 20230202134329.539625-2-rjarry@redhat.com (mailing list archive)
State Superseded, archived
Delegated to: David Marchand
Headers
Series lcore telemetry improvements |

Checks

Context Check Description
ci/checkpatch success coding style OK

Commit Message

Robin Jarry Feb. 2, 2023, 1:43 p.m. UTC
  Report the same information than rte_lcore_dump() in the telemetry
API into /eal/lcore/list and /eal/lcore/info,ID.

Example:

  --> /eal/lcore/info,3
  {
    "/eal/lcore/info": {
      "lcore_id": 3,
      "socket": 0,
      "role": "RTE",
      "cpuset": [
        3
      ]
    }
  }

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

Notes:
    v7 -> v8: made lcore_id integer parsing more robust

 lib/eal/common/eal_common_lcore.c | 123 +++++++++++++++++++++++++-----
 1 file changed, 105 insertions(+), 18 deletions(-)
  

Comments

Chengwen Feng Feb. 6, 2023, 3:50 a.m. UTC | #1
Hi Robin,

On 2023/2/2 21:43, Robin Jarry wrote:
> Report the same information than rte_lcore_dump() in the telemetry
> API into /eal/lcore/list and /eal/lcore/info,ID.
> 
> Example:
> 
>   --> /eal/lcore/info,3
>   {
>     "/eal/lcore/info": {
>       "lcore_id": 3,
>       "socket": 0,
>       "role": "RTE",
>       "cpuset": [
>         3
>       ]
>     }
>   }
> 

...

> +
> +static int
> +handle_lcore_info(const char *cmd __rte_unused, const char *params, struct rte_tel_data *d)
> +{
> +	struct lcore_telemetry_info info = { .d = d };
> +	unsigned long lcore_id;
> +	char *endptr;
> +
> +	if (params == NULL)
> +		return -EINVAL;
> +	errno = 0;
> +	lcore_id = strtoul(params, &endptr, 10);
> +	if (errno)
> +		return -errno;
> +	if (*params == '\0' || *endptr != '\0' || lcore_id >= RTE_MAX_LCORE)
> +		return -EINVAL;
> +
> +	info.lcore_id = lcore_id;
> +
> +	return rte_lcore_iterate(lcore_telemetry_info_cb, &info);

lcore_iterate will iterate and find the lcore.

How about add one new API e.g. rte_lcore_cb(xxx) ?

> +}
> +
> +RTE_INIT(lcore_telemetry)
> +{
> +	rte_telemetry_register_cmd(
> +		"/eal/lcore/list", handle_lcore_list,
> +		"List of lcore ids. Takes no parameters");
> +	rte_telemetry_register_cmd(
> +		"/eal/lcore/info", handle_lcore_info,
> +		"Returns lcore info. Parameters: int lcore_id");
> +}
> +#endif /* !RTE_EXEC_ENV_WINDOWS */
>
  
Robin Jarry Feb. 6, 2023, 8:22 a.m. UTC | #2
fengchengwen, Feb 06, 2023 at 04:50:
> > +	return rte_lcore_iterate(lcore_telemetry_info_cb, &info);
>
> lcore_iterate will iterate and find the lcore.
>
> How about add one new API e.g. rte_lcore_cb(xxx) ?

Hi fengchengwen,

what would that new API do?
  
Chengwen Feng Feb. 6, 2023, 11:22 a.m. UTC | #3
On 2023/2/6 16:22, Robin Jarry wrote:
> fengchengwen, Feb 06, 2023 at 04:50:
>> > +    return rte_lcore_iterate(lcore_telemetry_info_cb, &info);
>>
>> lcore_iterate will iterate and find the lcore.
>>
>> How about add one new API e.g. rte_lcore_cb(xxx) ?
> 
> Hi fengchengwen,
> 
> what would that new API do?

Just invoke callback on one specific lcore.

In this patch, the lcore_telemetry_info_cb() only valid on specific lcore, but it was implements by rte_lcore_iterate which will iterate all lcores.

> 
> 
> .
  
Robin Jarry Feb. 6, 2023, 11:46 a.m. UTC | #4
fengchengwen, Feb 06, 2023 at 12:22:
> Just invoke callback on one specific lcore.
>
> In this patch, the lcore_telemetry_info_cb() only valid on specific 
> lcore, but it was implements by rte_lcore_iterate which will iterate 
> all lcores.

Ok I see. I don't think this would be worth the effort. There will never 
be more than a few hundred cores. The performance gain would be 
negligible. What do you think?
  
Chengwen Feng Feb. 6, 2023, 12:08 p.m. UTC | #5
On 2023/2/6 19:46, Robin Jarry wrote:
> fengchengwen, Feb 06, 2023 at 12:22:
>> Just invoke callback on one specific lcore.
>>
>> In this patch, the lcore_telemetry_info_cb() only valid on specific lcore, but it was implements by rte_lcore_iterate which will iterate all lcores.
> 
> Ok I see. I don't think this would be worth the effort. There will never be more than a few hundred cores. The performance gain would be negligible. What do you think?

Okay for not add.

And for this patch,
Acked-by: Chengwen Feng <fengchengwen@huawei.com>

> 
> 
> .
  

Patch

diff --git a/lib/eal/common/eal_common_lcore.c b/lib/eal/common/eal_common_lcore.c
index 06c594b0224f..f53fc17b4d04 100644
--- a/lib/eal/common/eal_common_lcore.c
+++ b/lib/eal/common/eal_common_lcore.c
@@ -10,6 +10,9 @@ 
 #include <rte_errno.h>
 #include <rte_lcore.h>
 #include <rte_log.h>
+#ifndef RTE_EXEC_ENV_WINDOWS
+#include <rte_telemetry.h>
+#endif
 
 #include "eal_private.h"
 #include "eal_thread.h"
@@ -419,35 +422,35 @@  rte_lcore_iterate(rte_lcore_iterate_cb cb, void *arg)
 	return ret;
 }
 
+static const char *
+lcore_role_str(enum rte_lcore_role_t role)
+{
+	switch (role) {
+	case ROLE_RTE:
+		return "RTE";
+	case ROLE_SERVICE:
+		return "SERVICE";
+	case ROLE_NON_EAL:
+		return "NON_EAL";
+	default:
+		return "UNKNOWN";
+	}
+}
+
 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];
-	const char *role;
 	FILE *f = arg;
 	int ret;
 
-	switch (cfg->lcore_role[lcore_id]) {
-	case ROLE_RTE:
-		role = "RTE";
-		break;
-	case ROLE_SERVICE:
-		role = "SERVICE";
-		break;
-	case ROLE_NON_EAL:
-		role = "NON_EAL";
-		break;
-	default:
-		role = "UNKNOWN";
-		break;
-	}
-
 	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,
-		rte_lcore_to_socket_id(lcore_id), role, cpuset,
-		ret == 0 ? "" : "...");
+		rte_lcore_to_socket_id(lcore_id),
+		lcore_role_str(cfg->lcore_role[lcore_id]),
+		cpuset, ret == 0 ? "" : "...");
 	return 0;
 }
 
@@ -456,3 +459,87 @@  rte_lcore_dump(FILE *f)
 {
 	rte_lcore_iterate(lcore_dump_cb, f);
 }
+
+#ifndef RTE_EXEC_ENV_WINDOWS
+static int
+lcore_telemetry_id_cb(unsigned int lcore_id, void *arg)
+{
+	struct rte_tel_data *d = arg;
+	return rte_tel_data_add_array_int(d, lcore_id);
+}
+
+static int
+handle_lcore_list(const char *cmd __rte_unused,
+	const char *params __rte_unused,
+	struct rte_tel_data *d)
+{
+	int ret = rte_tel_data_start_array(d, RTE_TEL_INT_VAL);
+	if (ret)
+		return ret;
+	return rte_lcore_iterate(lcore_telemetry_id_cb, d);
+}
+
+struct lcore_telemetry_info {
+	unsigned int lcore_id;
+	struct rte_tel_data *d;
+};
+
+static int
+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_tel_data *cpuset;
+	unsigned int cpu;
+
+	if (info->lcore_id != lcore_id)
+		return 0;
+
+	rte_tel_data_start_dict(info->d);
+	rte_tel_data_add_dict_int(info->d, "lcore_id", lcore_id);
+	rte_tel_data_add_dict_int(info->d, "socket", rte_lcore_to_socket_id(lcore_id));
+	rte_tel_data_add_dict_string(info->d, "role", lcore_role_str(cfg->lcore_role[lcore_id]));
+	cpuset = rte_tel_data_alloc();
+	if (cpuset == NULL)
+		return -ENOMEM;
+	rte_tel_data_start_array(cpuset, RTE_TEL_INT_VAL);
+	for (cpu = 0; cpu < CPU_SETSIZE; cpu++) {
+		if (CPU_ISSET(cpu, &lcore_config[lcore_id].cpuset))
+			rte_tel_data_add_array_int(cpuset, cpu);
+	}
+	rte_tel_data_add_dict_container(info->d, "cpuset", cpuset, 0);
+
+	return 0;
+}
+
+static int
+handle_lcore_info(const char *cmd __rte_unused, const char *params, struct rte_tel_data *d)
+{
+	struct lcore_telemetry_info info = { .d = d };
+	unsigned long lcore_id;
+	char *endptr;
+
+	if (params == NULL)
+		return -EINVAL;
+	errno = 0;
+	lcore_id = strtoul(params, &endptr, 10);
+	if (errno)
+		return -errno;
+	if (*params == '\0' || *endptr != '\0' || lcore_id >= RTE_MAX_LCORE)
+		return -EINVAL;
+
+	info.lcore_id = lcore_id;
+
+	return rte_lcore_iterate(lcore_telemetry_info_cb, &info);
+}
+
+RTE_INIT(lcore_telemetry)
+{
+	rte_telemetry_register_cmd(
+		"/eal/lcore/list", handle_lcore_list,
+		"List of lcore ids. Takes no parameters");
+	rte_telemetry_register_cmd(
+		"/eal/lcore/info", handle_lcore_info,
+		"Returns lcore info. Parameters: int lcore_id");
+}
+#endif /* !RTE_EXEC_ENV_WINDOWS */