[PATCH v12 3/3] examples/l3fwd-power: add PM QoS configuration

[Konstantin Ananyev]

> The '--cpu-resume-latency' can use to control C-state selection.
> Setting the CPU resume latency to 0 can limit the CPU just to enter
> C0-state to improve performance, which also may increase the power
> consumption of platform.
> 
> Signed-off-by: Huisong Li <lihuisong at huawei.com>
> Acked-by: Morten Brørup <mb at smartsharesystems.com>
> Acked-by: Chengwen Feng <fengchengwen at huawei.com>
> ---
>  .../sample_app_ug/l3_forward_power_man.rst    |  5 +-
>  examples/l3fwd-power/main.c                   | 68 +++++++++++++++++++
>  2 files changed, 72 insertions(+), 1 deletion(-)
> 
> diff --git a/doc/guides/sample_app_ug/l3_forward_power_man.rst b/doc/guides/sample_app_ug/l3_forward_power_man.rst
> index 9c9684fea7..70fa83669a 100644
> --- a/doc/guides/sample_app_ug/l3_forward_power_man.rst
> +++ b/doc/guides/sample_app_ug/l3_forward_power_man.rst
> @@ -67,7 +67,8 @@ based on the speculative sleep duration of the core.
>  In this application, we introduce a heuristic algorithm that allows packet processing cores to sleep for a short period
>  if there is no Rx packet received on recent polls.
>  In this way, CPUIdle automatically forces the corresponding cores to enter deeper C-states
> -instead of always running to the C0 state waiting for packets.
> +instead of always running to the C0 state waiting for packets. But user can set the CPU resume latency to control C-state selection.
> +Setting the CPU resume latency to 0 can limit the CPU just to enter C0-state to improve performance, which may increase power
> consumption of platform.
> 
>  .. note::
> 
> @@ -105,6 +106,8 @@ where,
> 
>  *   --config (port,queue,lcore)[,(port,queue,lcore)]: determines which queues from which ports are mapped to which cores.
> 
> +*   --cpu-resume-latency LATENCY: set CPU resume latency to control C-state selection, 0 : just allow to enter C0-state.
> +
>  *   --max-pkt-len: optional, maximum packet length in decimal (64-9600)
> 
>  *   --no-numa: optional, disables numa awareness
> diff --git a/examples/l3fwd-power/main.c b/examples/l3fwd-power/main.c
> index 0ce4aa04d4..e58f4e301c 100644
> --- a/examples/l3fwd-power/main.c
> +++ b/examples/l3fwd-power/main.c
> @@ -47,6 +47,7 @@
>  #include <rte_telemetry.h>
>  #include <rte_power_pmd_mgmt.h>
>  #include <rte_power_uncore.h>
> +#include <rte_power_qos.h>
> 
>  #include "perf_core.h"
>  #include "main.h"
> @@ -265,6 +266,9 @@ static uint32_t pause_duration = 1;
>  static uint32_t scale_freq_min;
>  static uint32_t scale_freq_max;
> 
> +static int cpu_resume_latency;
> +static bool pm_qos_en;
> +
>  static struct rte_mempool * pktmbuf_pool[NB_SOCKETS];
> 
> 
> @@ -1501,6 +1505,8 @@ print_usage(const char *prgname)
>  		"  -U: set min/max frequency for uncore to maximum value\n"
>  		"  -i (frequency index): set min/max frequency for uncore to specified frequency index\n"
>  		"  --config (port,queue,lcore): rx queues configuration\n"
> +		"  --cpu-resume-latency LATENCY: set CPU resume latency to control C-state selection,"
> +		" 0 : just allow to enter C0-state\n"
>  		"  --high-perf-cores CORELIST: list of high performance cores\n"
>  		"  --perf-config: similar as config, cores specified as indices"
>  		" for bins containing high or regular performance cores\n"
> @@ -1545,6 +1551,28 @@ parse_uint32(const char *opt, uint32_t *res)
>  	return 0;
>  }
> 
> +static int
> +parse_int(const char *opt, int *res)
> +{
> +	char *end = NULL;
> +	signed long val;
> +
> +	/* parse integer string */
> +	val = strtol(opt, &end, 10);
> +	if ((opt[0] == '\0') || (end == NULL) || (*end != '\0'))
> +		return -1;
> +
> +	if (val < INT_MIN || val > INT_MAX) {
> +		RTE_LOG(ERR, L3FWD_POWER, "parameter should be range from %d to %d.\n",
> +			INT_MIN, INT_MAX);
> +		return -1;
> +	}
> +
> +	*res = val;
> +
> +	return 0;
> +}
> +
>  static int
>  parse_uncore_options(enum uncore_choice choice, const char *argument)
>  {
> @@ -1734,6 +1762,7 @@ parse_pmd_mgmt_config(const char *name)
>  #define CMD_LINE_OPT_PAUSE_DURATION "pause-duration"
>  #define CMD_LINE_OPT_SCALE_FREQ_MIN "scale-freq-min"
>  #define CMD_LINE_OPT_SCALE_FREQ_MAX "scale-freq-max"
> +#define CMD_LINE_OPT_CPU_RESUME_LATENCY "cpu-resume-latency"
> 
>  /* Parse the argument given in the command line of the application */
>  static int
> @@ -1748,6 +1777,7 @@ parse_args(int argc, char **argv)
>  		{"perf-config", 1, 0, 0},
>  		{"high-perf-cores", 1, 0, 0},
>  		{"no-numa", 0, 0, 0},
> +		{CMD_LINE_OPT_CPU_RESUME_LATENCY, 1, 0, 0},
>  		{CMD_LINE_OPT_MAX_PKT_LEN, 1, 0, 0},
>  		{CMD_LINE_OPT_PARSE_PTYPE, 0, 0, 0},
>  		{CMD_LINE_OPT_LEGACY, 0, 0, 0},
> @@ -1933,6 +1963,15 @@ parse_args(int argc, char **argv)
>  				printf("Scaling frequency maximum configured\n");
>  			}
> 
> +			if (!strncmp(lgopts[option_index].name,
> +					CMD_LINE_OPT_CPU_RESUME_LATENCY,
> +					sizeof(CMD_LINE_OPT_CPU_RESUME_LATENCY))) {
> +				if (parse_int(optarg, &cpu_resume_latency) != 0)

Do you really need a to support a negative values for that variable?

> +					return -1;
> +				printf("PM QoS configured\n");
> +				pm_qos_en = true;
> +			}
> +
>  			break;
> 
>  		default:
> @@ -2256,6 +2295,26 @@ init_power_library(void)
>  			return -1;
>  		}
>  	}
> +
> +	if (pm_qos_en) {
> +		RTE_LCORE_FOREACH(lcore_id) {
> +			/*
> +			 * Set the cpu resume latency of the worker lcore based
> +			 * on user's request. If set strict latency (0), just
> +			 * allow the CPU to enter the shallowest idle state to
> +			 * improve performance.
> +			 */
> +			ret = rte_power_qos_set_cpu_resume_latency(lcore_id,
> +							cpu_resume_latency);
> +			if (ret != 0) {
> +				RTE_LOG(ERR, L3FWD_POWER,
> +					"Failed to set cpu resume latency on lcore-%u.\n",
> +					lcore_id);
> +				return ret;
> +			}
> +		}
> +	}
> +
>  	return ret;
>  }
> 
> @@ -2295,6 +2354,15 @@ deinit_power_library(void)
>  			}
>  		}
>  	}
> +
> +	if (pm_qos_en) {
> +		RTE_LCORE_FOREACH(lcore_id) {
> +			/* Restore the original value in kernel. */
> +			rte_power_qos_set_cpu_resume_latency(lcore_id,
> +					RTE_POWER_QOS_RESUME_LATENCY_NO_CONSTRAINT);

If we are going to 'restore original' shouldn't we:
At startup old_value=get() 
At termination: set(old_value)
?  

> +		}
> +	}
> +
>  	return ret;
>  }
> 
> --
> 2.22.0