[PATCH v2 3/4] examples/dma: support enqueue drop statistic

fengchengwen fengchengwen at huawei.com
Sun Apr 24 05:55:26 CEST 2022


After thinking about it, there are other ways (e.g. dmadump/telemetry) to know
which failed, so I think we could drop this patch.

I will send v3 for other patches.

Thanks.

On 2022/4/19 20:09, fengchengwen wrote:
> On 2022/4/19 16:45, Bruce Richardson wrote:
>> On Sat, Apr 16, 2022 at 02:19:24PM +0800, fengchengwen wrote:
>>> DMA is a memcopy engine, and from that perspective, I think it's appropriate
>>> to use copy_failures when dma_enqueue fails.
>>>
>>> The newly added enqueue_failures is mainly used for rte_ring_enqueue_burst
>>> failures.
>>>
>>> Since the app doesn't have a command line, I think adding this field can
>>> immediately identify where it failed.
>>>
>>
>> So one stat is for the HW path and the other is for the SW one? If that is
>> the case, only one stat should probably be printed out by the app depending
>> on the mode is it in.
> 
> For HW path, both copy_failures and enqueue_failures
> For SW path, only the enqueue_failure, PS: the value of copy_failures is fixed to be 0
> 
>>
>>> On 2022/4/13 23:01, Bruce Richardson wrote:
>>>> On Mon, Apr 11, 2022 at 08:14:58PM +0800, Chengwen Feng wrote:
>>>>> The copy drop statistic counted in two scenarios: DMA copy failures and
>>>>> enqueue failures. so it is difficult to locate the problem.
>>>>>
>>>>
>>>> Is the app actually tracking copy failures? From a quick glance at the code
>>>> it looks to me like the only "copy_failures" are the enqueue failures, in
>>>> which case the stat should just be renamed.
>>>>
>>>>> This patch adds enqueue drop statistic to fix the it.
>>>>>
>>>>> Signed-off-by: Chengwen Feng <fengchengwen at huawei.com>
>>>>> ---
>>>>>  examples/dma/dmafwd.c | 14 +++++++++-----
>>>>>  1 file changed, 9 insertions(+), 5 deletions(-)
>>>>>
>>>>
>>>> .
>>>>
>>>
>>
>> .
>>
> 
> 
> .
> 



More information about the dev mailing list