[PATCH 5/5] app/testpmd: add error recovery usage demo

[fengchengwen]

On 2023/3/2 21:01, Konstantin Ananyev wrote:
> 
> 
>>
>> This patch adds error recovery usage demo which will:
>> 1. stop packet forwarding when the RTE_ETH_EVENT_ERR_RECOVERING event
>>    is received.
>> 2. restart packet forwarding when the RTE_ETH_EVENT_RECOVERY_SUCCESS
>>    event is received.
>> 3. prompt the ports that fail to recovery and need to be removed when
>>    the RTE_ETH_EVENT_RECOVERY_FAILED event is received.
>>
>> In addition, a message is added to the printed information, requiring
>> no command to be executed during the error recovery.
>>
>> Signed-off-by: Chengwen Feng <fengchengwen at huawei.com>
>> ---
>>  app/test-pmd/testpmd.c | 80 ++++++++++++++++++++++++++++++++++++++++++
>>  app/test-pmd/testpmd.h |  4 ++-
>>  2 files changed, 83 insertions(+), 1 deletion(-)
>>
>> diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/testpmd.c
>> index 0c14325b8d..fdc3ae604b 100644
>> --- a/app/test-pmd/testpmd.c
>> +++ b/app/test-pmd/testpmd.c
>> @@ -3823,6 +3823,77 @@ rmv_port_callback(void *arg)
>>  		start_packet_forwarding(0);
>>  }
>>
>> +static int need_start_when_recovery_over;
>> +
>> +static bool
>> +has_port_in_err_recovering(void)
>> +{
>> +	struct rte_port *port;
>> +	portid_t pid;
>> +
>> +	RTE_ETH_FOREACH_DEV(pid) {
>> +		port = &ports[pid];
>> +		if (port->err_recovering)
>> +			return true;
>> +	}
>> +
>> +	return false;
>> +}
>> +
>> +static void
>> +err_recovering_callback(portid_t port_id)
>> +{
>> +	if (!has_port_in_err_recovering())
>> +		printf("Please stop executing any commands until recovery result events are received!\n");
>> +
>> +	ports[port_id].err_recovering = 1;
>> +	ports[port_id].recover_failed = 0;
>> +
>> +	/* To simplify implementation, stop forwarding regardless of whether the port is used. */
>> +	if (!test_done) {
>> +		printf("Stop packet forwarding because some ports are in error recovering!\n");
>> +		stop_packet_forwarding();
>> +		need_start_when_recovery_over = 1;
>> +	}
>> +}
> 
> One thought I have - should we somehow stop user to attempt restart RX/TX while recovery
> in progress?
> But probably it is an overkill, and just documenting what is happening is enough....

Yes, the testpmd is already complicated.
In addition, considering that only a few PMDs support and are not commonly invoking.
So I thinking show above such promote is enough.

> Do we need to update testpmd UG with some short description?

It's better to update UG, but it wasn't triggered by command, I don't know which chapter to put it in.

@Ferruh could you provide some advise ?

> Apart from that, LGTM:
> Acked-by: Konstantin Ananyev <konstantin.ananyev at huawei.com>
> 
>> +
>> +static void
>> +recover_success_callback(portid_t port_id)
>> +{
>> +	ports[port_id].err_recovering = 0;
>> +	if (has_port_in_err_recovering())
>> +		return;
>> +
>> +	if (need_start_when_recovery_over) {
>> +		printf("Recovery success! Restart packet forwarding!\n");
>> +		start_packet_forwarding(0);
>> +		need_start_when_recovery_over = 0;
>> +	} else {
>> +		printf("Recovery success!\n");
>> +	}
>> +}
>> +
>> +static void
>> +recover_failed_callback(portid_t port_id)
>> +{
>> +	struct rte_port *port;
>> +	portid_t pid;
>> +
>> +	ports[port_id].err_recovering = 0;
>> +	ports[port_id].recover_failed = 1;
>> +	if (has_port_in_err_recovering())
>> +		return;
>> +
>> +	need_start_when_recovery_over = 0;
>> +	printf("The ports:");
>> +	RTE_ETH_FOREACH_DEV(pid) {
>> +		port = &ports[pid];
>> +		if (port->recover_failed)
>> +			printf(" %u", pid);
>> +	}
>> +	printf(" recovery failed! Please remove them!\n");
>> +}
>> +
>>  /* This function is used by the interrupt thread */
>>  static int
>>  eth_event_callback(portid_t port_id, enum rte_eth_event_type type, void *param,
>> @@ -3878,6 +3949,15 @@ eth_event_callback(portid_t port_id, enum rte_eth_event_type type, void *param,
>>  		}
>>  		break;
>>  	}
>> +	case RTE_ETH_EVENT_ERR_RECOVERING:
>> +		err_recovering_callback(port_id);
>> +		break;
>> +	case RTE_ETH_EVENT_RECOVERY_SUCCESS:
>> +		recover_success_callback(port_id);
>> +		break;
>> +	case RTE_ETH_EVENT_RECOVERY_FAILED:
>> +		recover_failed_callback(port_id);
>> +		break;
>>  	default:
>>  		break;
>>  	}
>> diff --git a/app/test-pmd/testpmd.h b/app/test-pmd/testpmd.h
>> index 329a6378a1..1bbf82a96c 100644
>> --- a/app/test-pmd/testpmd.h
>> +++ b/app/test-pmd/testpmd.h
>> @@ -323,7 +323,9 @@ struct rte_port {
>>  	uint8_t                 slave_flag : 1, /**< bonding slave port */
>>  				bond_flag : 1, /**< port is bond device */
>>  				fwd_mac_swap : 1, /**< swap packet MAC before forward */
>> -				update_conf : 1; /**< need to update bonding device configuration */
>> +				update_conf : 1, /**< need to update bonding device configuration */
>> +				err_recovering : 1, /**< port is in error recovering */
>> +				recover_failed : 1; /**< port recover failed */
>>  	struct port_template    *pattern_templ_list; /**< Pattern templates. */
>>  	struct port_template    *actions_templ_list; /**< Actions templates. */
>>  	struct port_table       *table_list; /**< Flow tables. */
>> --
>> 2.17.1
> 
> .
>