Re: [RFC PATCH 5/5] can: m_can: Add hrtimer to generate software interrupt

From: "Mendez, Judith" <jm@ti.com>
To: Marc Kleine-Budde <mkl@pengutronix.de>
Cc: Oliver Hartkopp <socketcan@hartkopp.net>,
	Chandrasekar Ramakrishnan <rcsekar@samsung.com>,
	Nishanth Menon <nm@ti.com>, Vignesh Raghavendra <vigneshr@ti.com>,
	Andrew Davis <afd@ti.com>,
	Wolfgang Grandegger <wg@grandegger.com>,
	Rob Herring <robh+dt@kernel.org>,
	Krzysztof Kozlowski <krzysztof.kozlowski+dt@linaro.org>,
	<linux-can@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
	<devicetree@vger.kernel.org>, <netdev@vger.kernel.org>,
	Schuyler Patton <spatton@ti.com>
Subject: Re: [RFC PATCH 5/5] can: m_can: Add hrtimer to generate software interrupt
Date: Wed, 19 Apr 2023 09:38:58 -0500	[thread overview]
Message-ID: <5d81aeb6-2b52-5807-5b42-daa87767144f@ti.com> (raw)
In-Reply-To: <20230419-trimmer-fasting-928868e8cb81-mkl@pengutronix.de>

Hello Marc,

On 4/19/2023 1:13 AM, Marc Kleine-Budde wrote:
> On 18.04.2023 15:59:57, Mendez, Judith wrote:
>>>>>>>> The "shortest" 11 bit CAN ID CAN frame is a Classical CAN frame with DLC = 0
>>>>>>>> and 1 Mbit/s (arbitration) bitrate. This should be 48 bits @1Mbit => ~50
>>>>>>>> usecs
>>>>>>>>
>>>>>>>> So it should be something about
>>>>>>>>
>>>>>>>>         50 usecs * (FIFO queue len - 2)
>>>>>>>
>>>>>>> Where does the "2" come from?
>>>>>>
>>>>>> I thought about handling the FIFO earlier than it gets completely "full".
>>>>>>
>>>>>> The fetching routine would need some time too and the hrtimer could also
>>>>>> jitter to some extend.
>>>>>
>>>>> I was assuming something like this.
>>>>>
>>>>> I would argue that the polling time should be:
>>>>>
>>>>>        50 µs * FIFO length - IRQ overhead.
>>>>>
>>>>> The max IRQ overhead depends on your SoC and kernel configuration.
>>>>
>>>> I just tried an educated guess to prevent the FIFO to be filled up
>>>> completely. How can you estimate the "IRQ overhead"? And how do you catch
>>>> the CAN frames that are received while the IRQ is handled?
>>>
>>> We're talking about polling, better call it "overhead" or "latency from
>>> timer expiration until FIFO has at least one frame room". This value
>>> depends on your system.
>>>
>>> It depends on many, many factors, SoC, Kernel configuration (preempt RT,
>>> powersaving, frequency scaling, system load. In your example it's 100
>>> µs. I wanted to say there's an overhead (or latency) and we need enough
>>> space in the FIFO, to cover it.
>>>
>>
>> I am not sure how to estimate IRQ overhead, but FIFO length should be 64
>> elements.
> 
> Ok
> 
>> 50 us * 62 is about 3.1 ms and we are using 1 ms timer polling interval.
> 
> Sounds good.
> 
>> Running a few benchmarks showed that using 0.5 ms timer polling interval
>> starts to take a toll on CPU load, that is why I chose 1 ms polling
>> interval.
> 
> However in the code you use 5 ms.

Yes, it was a mistake, will send out a respin with the correct value, 
thanks.

regards,
Judith