Hi,
Alan Stern writes:
> On Fri, 9 Oct 2015, Felipe Balbi wrote:
>
>> that's all clear :-) The point is that I _do_ get a ton of PINGs because
>> the gadget doesn't queue requests fast enough and I'm, currently,
>> blaming the latency of the kthread() itself, though I haven't been
>> successful
On Fri, 9 Oct 2015, Felipe Balbi wrote:
> that's all clear :-) The point is that I _do_ get a ton of PINGs because
> the gadget doesn't queue requests fast enough and I'm, currently,
> blaming the latency of the kthread() itself, though I haven't been
> successful at proving that statement thus fa
Hi,
Peter Chen writes:
> On Fri, Oct 02, 2015 at 11:05:28AM -0500, Felipe Balbi wrote:
>> Hi Alan,
>>
>> here's a question which I hope you can help me understand :-)
>>
>> Why do we have that kthread for the mass storage gadgets ? I noticed a very
>> interesting behavior.
>>
>> Basically, th
On Fri, Oct 02, 2015 at 11:05:28AM -0500, Felipe Balbi wrote:
> Hi Alan,
>
> here's a question which I hope you can help me understand :-)
>
> Why do we have that kthread for the mass storage gadgets ? I noticed a very
> interesting behavior.
>
> Basically, the MSC class works in a loop like so:
Hi,
On Fri, Oct 02, 2015 at 02:57:54PM -0400, Alan Stern wrote:
> On Fri, 2 Oct 2015, Felipe Balbi wrote:
>
> > > Figure [1] is misleading. The 7 POLLs you see are at the very start of
> > > a READ. It's not surprising that the host can poll 7 times before the
> > > gadget manages to read the
On Fri, 2 Oct 2015, Felipe Balbi wrote:
> > Figure [1] is misleading. The 7 POLLs you see are at the very start of
> > a READ. It's not surprising that the host can poll 7 times before the
> > gadget manages to read the first block of data from the backing file.
> > This isn't a case where t
On Fri, Oct 02, 2015 at 01:29:05PM -0400, Alan Stern wrote:
> On Fri, 2 Oct 2015, Felipe Balbi wrote:
>
> > Hi Alan,
> >
> > here's a question which I hope you can help me understand :-)
> >
> > Why do we have that kthread for the mass storage gadgets ? I noticed a very
> > interesting behavior.
On Fri, 2 Oct 2015, Felipe Balbi wrote:
> Hi Alan,
>
> here's a question which I hope you can help me understand :-)
>
> Why do we have that kthread for the mass storage gadgets ? I noticed a very
> interesting behavior.
Basically, the mass-storage gadget uses a kthread in order to access
the b
Hi Alan,
here's a question which I hope you can help me understand :-)
Why do we have that kthread for the mass storage gadgets ? I noticed a very
interesting behavior.
Basically, the MSC class works in a loop like so:
CBW
Data Transfer
CSW
In our implemention, what we do is:
CBW
wake_up_proc
