On Mon Jun 22 2020, Andrew Lunn wrote:
> On Mon, Jun 22, 2020 at 02:32:28PM +0200, Kurt Kanzenbach wrote:
>> On Fri Jun 19 2020, Andrew Lunn wrote:
>> >> > Are trace registers counters?
>> >>
>> >> No. The trace registers provide bits for error conditions and if packets
>> >> have been dropped e.g
Hi Vladimir,
On Mon Jun 22 2020, Vladimir Oltean wrote:
> Hi Kurt,
>
> On Mon, 22 Jun 2020 at 15:34, Kurt Kanzenbach wrote:
>>
>> * Re-prioritization of packets based on the ether type (not mac address)
>
> This can be done by offloading a tc skbedit priority action, and a
> "protocol" key (even
Hi Kurt,
On Mon, 22 Jun 2020 at 15:34, Kurt Kanzenbach wrote:
>
> * Re-prioritization of packets based on the ether type (not mac address)
This can be done by offloading a tc skbedit priority action, and a
"protocol" key (even though I don't understand why you need to mention
"not mac address".
On Mon, Jun 22, 2020 at 02:32:28PM +0200, Kurt Kanzenbach wrote:
> On Fri Jun 19 2020, Andrew Lunn wrote:
> >> > Are trace registers counters?
> >>
> >> No. The trace registers provide bits for error conditions and if packets
> >> have been dropped e.g. because of full queues or FCS errors, and so
On Fri Jun 19 2020, Andrew Lunn wrote:
>> > Are trace registers counters?
>>
>> No. The trace registers provide bits for error conditions and if packets
>> have been dropped e.g. because of full queues or FCS errors, and so on.
>
> Is there some documentation somewhere? A better understanding of w
> > Are trace registers counters?
>
> No. The trace registers provide bits for error conditions and if packets
> have been dropped e.g. because of full queues or FCS errors, and so on.
Is there some documentation somewhere? A better understanding of what
they can do might help figure out the corr
Hi Andrew,
On Thu Jun 18 2020, Andrew Lunn wrote:
> On Thu, Jun 18, 2020 at 08:40:26AM +0200, Kurt Kanzenbach wrote:
>> The switch has registers which are useful for debugging issues:
>
> debugfs is not particularly likes. Please try to find other means
> where possible. Memory usage fits nicely i
On Thu, Jun 18, 2020 at 08:40:26AM +0200, Kurt Kanzenbach wrote:
> The switch has registers which are useful for debugging issues:
debugfs is not particularly likes. Please try to find other means
where possible. Memory usage fits nicely into devlink. See mv88e6xxx
which exports the ATU fill for e
The switch has registers which are useful for debugging issues:
* Trace registers
This can be helpful to trace why packets have been filtered or dropped or if
there any other serious problems.
* Memory registers
These registers provide the current switch internal RAM
utilization.
