Re: [dpdk-dev] [PATCH v4 3/6] app/testpmd: remove restriction on txpkts set

[Ferruh Yigit <ferruh.yigit@intel.com>]

On 11/26/2020 7:24 AM, Slava Ovsiienko wrote:
> The bug: https://bugs.dpdk.org/show_bug.cgi?id=584
> 
> Can we pass the nb_segs = 1 always?
> One descriptor is minimal basic capability to send, it should be always supported.
> 

Hi Slava,

I didn't get your comment, can you please elaborate?


> With best regards, Slava
> 
>> -----Original Message-----
>> From: Ferruh Yigit <ferruh.yigit@intel.com>
>> Sent: Wednesday, November 25, 2020 16:07
>> To: NBU-Contact-Thomas Monjalon <thomas@monjalon.net>; Wei Hu (Xavier)
>> <huwei013@chinasoftinc.com>
>> Cc: dev@dpdk.org; xavier.huwei@huawei.com; Slava Ovsiienko
>> <viacheslavo@nvidia.com>
>> Subject: Re: [dpdk-dev] [PATCH v4 3/6] app/testpmd: remove restriction on
>> txpkts set
>>
>> On 11/24/2020 12:23 PM, Ferruh Yigit wrote:
>>> On 11/24/2020 10:27 AM, Thomas Monjalon wrote:
>>>> Is it OK to keep this regression?
>>>>
>>>> Ferruh, what do you suggest?
>>>>
>>>
>>> I confirm the '--txpkts' parameter is broken now, I suggest submitting
>>> a defect for it and continue with the regression.
>>>
>>
>> Hi Slava,
>>
>> Can you please submit the Bugzilla defect?
>>
>> Thanks,
>> ferruh
>>
>>
>>> We have alternative for the parameter, "set txpkts <len0[,len1]*>" command.
>>> The parameter was only working when hardcoded '--txd=N' parameter is
>>> provided, the command is more dynamic and works however queue size is
>> configured.
>>>
>>> We can fix the '--txpkts' in next release.
>>>
>>>>
>>>> 23/11/2020 12:50, Slava Ovsiienko:
>>>>> Hi,  Wei
>>>>>
>>>>> It was found this patch rejects the --txpkts command line settings.
>>>>> set_tx_pkt_segments() is called before device started and we have
>>>>> failure chain:
>>>>>
>>>>> set_tx_pkt_segments()
>>>>>     nb_segs_is_invalid()
>>>>>       get_tx_ring_size ()
>>>>>        rte_eth_tx_queue_info_get()
>>>>>
>>>>> It causes --txpkts testpmd command line option is ignored.
>>>>>
>>>>> With best regards, Slava
>>>>>
>>>>>> -----Original Message-----
>>>>>> From: dev <dev-bounces@dpdk.org> On Behalf Of Wei Hu (Xavier)
>>>>>> Sent: Friday, September 25, 2020 15:47
>>>>>> To: dev@dpdk.org
>>>>>> Cc: xavier.huwei@huawei.com
>>>>>> Subject: [dpdk-dev] [PATCH v4 3/6] app/testpmd: remove restriction
>>>>>> on txpkts set
>>>>>>
>>>>>> From: Chengchang Tang <tangchengchang@huawei.com>
>>>>>>
>>>>>> Currently, if nb_txd is not set, the txpkts is not allowed to be
>>>>>> set because the nb_txd is used to avoid the numer of segments
>>>>>> exceed the Tx ring size and the default value of nb_txd is 0. And
>>>>>> there is a bug that nb_txd is the global configuration for Tx ring
>>>>>> size and the ring size could be changed by some command per queue.
>>>>>> So these valid check is unreliable and introduced unnecessary
>>>>>> constraints.
>>>>>>
>>>>>> This patch adds a valid check function to use the real Tx ring size
>>>>>> to check the validity of txpkts.
>>>>>>
>>>>>> Fixes: af75078fece3 ("first public release")
>>>>>> Cc: stable@dpdk.org
>>>>>>
>>>>>> Signed-off-by: Chengchang Tang <tangchengchang@huawei.com>
>>>>>> Signed-off-by: Wei Hu (Xavier) <xavier.huwei@huawei.com>
>>>>>> ---
>>>>>> v3 -> v4:
>>>>>>       add check 'rte_eth_rx_queue_info_get()' return value and
>>>>>>       if it is '-ENOSTUP' calculate the 'ring_size'.
>>>>>> v3:      initial version.
>>>>>> ---
>>>>>>    app/test-pmd/config.c | 64
>>>>>> +++++++++++++++++++++++++++++++++++++++++++++++----
>>>>>>    1 file changed, 60 insertions(+), 4 deletions(-)
>>>>>>
>>>>>> diff --git a/app/test-pmd/config.c b/app/test-pmd/config.c index
>>>>>> 6496d2f..8ebb927 100644
>>>>>> --- a/app/test-pmd/config.c
>>>>>> +++ b/app/test-pmd/config.c
>>>>>> @@ -1893,6 +1893,38 @@ tx_queue_id_is_invalid(queueid_t txq_id)  }
>>>>>>
>>>>>>    static int
>>>>>> +get_tx_ring_size(portid_t port_id, queueid_t txq_id, uint16_t
>>>>>> +*ring_size) {
>>>>>> +    struct rte_port *port = &ports[port_id];
>>>>>> +    struct rte_eth_txq_info tx_qinfo;
>>>>>> +    int ret;
>>>>>> +
>>>>>> +    ret = rte_eth_tx_queue_info_get(port_id, txq_id, &tx_qinfo);
>>>>>> +    if (ret == 0) {
>>>>>> +        *ring_size = tx_qinfo.nb_desc;
>>>>>> +        return ret;
>>>>>> +    }
>>>>>> +
>>>>>> +    if (ret != -ENOTSUP)
>>>>>> +        return ret;
>>>>>> +    /*
>>>>>> +     * If the rte_eth_tx_queue_info_get is not support for this
>>>>>> +PMD,
>>>>>> +     * ring_size stored in testpmd will be used for validity verification.
>>>>>> +     * When configure the txq by rte_eth_tx_queue_setup with
>>>>>> nb_tx_desc
>>>>>> +     * being 0, it will use a default value provided by PMDs to
>>>>>> +setup this
>>>>>> +     * txq. If the default value is 0, it will use the
>>>>>> +     * RTE_ETH_DEV_FALLBACK_TX_RINGSIZE to setup this txq.
>>>>>> +     */
>>>>>> +    if (port->nb_tx_desc[txq_id])
>>>>>> +        *ring_size = port->nb_tx_desc[txq_id];
>>>>>> +    else if (port->dev_info.default_txportconf.ring_size)
>>>>>> +        *ring_size = port->dev_info.default_txportconf.ring_size;
>>>>>> +    else
>>>>>> +        *ring_size = RTE_ETH_DEV_FALLBACK_TX_RINGSIZE;
>>>>>> +    return 0;
>>>>>> +}
>>>>>> +
>>>>>> +static int
>>>>>>    rx_desc_id_is_invalid(uint16_t rxdesc_id)  {
>>>>>>        if (rxdesc_id < nb_rxd)
>>>>>> @@ -2986,17 +3018,41 @@ show_tx_pkt_segments(void)
>>>>>>        printf("Split packet: %s\n", split);
>>>>>>    }
>>>>>>
>>>>>> +static bool
>>>>>> +nb_segs_is_invalid(unsigned int nb_segs) {
>>>>>> +    uint16_t ring_size;
>>>>>> +    uint16_t queue_id;
>>>>>> +    uint16_t port_id;
>>>>>> +    int ret;
>>>>>> +
>>>>>> +    RTE_ETH_FOREACH_DEV(port_id) {
>>>>>> +        for (queue_id = 0; queue_id < nb_txq; queue_id++) {
>>>>>> +            ret = get_tx_ring_size(port_id, queue_id, &ring_size);
>>>>>> +
>>>>>> +            if (ret)
>>>>>> +                return true;
>>>>>> +
>>>>>> +            if (ring_size < nb_segs) {
>>>>>> +                printf("nb segments per TX packets=%u >= "
>>>>>> +                       "TX queue(%u) ring_size=%u - ignored\n",
>>>>>> +                       nb_segs, queue_id, ring_size);
>>>>>> +                return true;
>>>>>> +            }
>>>>>> +        }
>>>>>> +    }
>>>>>> +
>>>>>> +    return false;
>>>>>> +}
>>>>>> +
>>>>>>    void
>>>>>>    set_tx_pkt_segments(unsigned *seg_lengths, unsigned nb_segs)  {
>>>>>>        uint16_t tx_pkt_len;
>>>>>>        unsigned i;
>>>>>>
>>>>>> -    if (nb_segs >= (unsigned) nb_txd) {
>>>>>> -        printf("nb segments per TX packets=%u >= nb_txd=%u -
>>>>>> ignored\n",
>>>>>> -               nb_segs, (unsigned int) nb_txd);
>>>>>> +    if (nb_segs_is_invalid(nb_segs))
>>>>>>            return;
>>>>>> -    }
>>>>>>
>>>>>>        /*
>>>>>>         * Check that each segment length is greater or equal than
>>>>>> --
>>>>>> 2.9.5
>>>>>
>>>>>
>>>>
>>>>
>>>>
>>>>
>>>>
>>>
>